© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 35332
    Prev
    Next
    INDEX
    Explanations

    information related to violent events, attacks, and security incidents involving significant casualties or threats

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.16
    0.8%
    260
    +0.10
    0.4%
    627
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    639
    +0.16
    0.09
    516
    +0.10
    0.06
    694
    +0.09
    0.01
    Negative Logits
    wcsstore
    -0.71
     evolves
    -0.71
     disclaimer
    -0.70
     Transactions
    -0.68
    soType
    -0.67
     Printed
    -0.67
    inventoryQuantity
    -0.66
    istries
    -0.66
    Management
    -0.65
    soDeliveryDate
    -0.65
    POSITIVE LOGITS
     bystanders
    0.95
     unarmed
    0.94
     innocent
    0.94
     civilians
    0.88
     wounding
    0.85
     injuring
    0.82
     fleeing
    0.82
     hostages
    0.82
     unborn
    0.82
     victims
    0.81
    Activations Density 9.791%

    No Known Activations