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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 35018
    Prev
    Next
    INDEX
    Explanations

    phrases related to military conflicts and incidents

    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%
    469
    +0.09
    0.5%
    221
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    553
    +0.16
    0.07
    362
    +0.09
    0.10
    270
    +0.09
    0.05
    Negative Logits
    lege
    -0.61
    isd
    -0.58
    username
    -0.58
    lore
    -0.57
    emonic
    -0.56
    thin
    -0.56
    reated
    -0.56
    anto
    -0.55
    creation
    -0.54
     disclaimer
    -0.54
    POSITIVE LOGITS
     helicopters
    0.71
     unarmed
    0.71
    abad
    0.70
     747
    0.70
     helicopter
    0.67
     jets
    0.67
     airplanes
    0.64
     bombing
    0.62
     drones
    0.61
     remotely
    0.60
    Activations Density 8.084%

    No Known Activations