© 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. 32474
    Prev
    Next
    INDEX
    Explanations

    images related to violence and physical attacks

    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
    68
    +0.12
    0.6%
    533
    +0.11
    0.5%
    735
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    68
    +0.12
    0.04
    482
    +0.11
    0.04
    271
    +0.10
    0.03
    Negative Logits
    BALL
    -0.72
     Barg
    -0.70
    FAULT
    -0.62
     Fields
    -0.61
    èĢħ
    -0.60
    inals
    -0.60
    Released
    -0.59
     Kahn
    -0.59
     Munich
    -0.58
    BUT
    -0.58
    POSITIVE LOGITS
    dates
    0.82
     appearances
    0.79
     footing
    0.79
    ruciating
    0.78
    endra
    0.73
    earance
    0.72
    cycles
    0.72
    iments
    0.69
    cycl
    0.68
    idth
    0.68
    Activations Density 4.720%

    No Known Activations