© 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. 31494
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical appearance or characteristics

    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
    +0.17
    1.0%
    408
    +0.10
    0.6%
    159
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.17
    0.15
    447
    +0.10
    0.17
    159
    +0.09
    0.11
    Negative Logits
    âķIJâķIJ
    -0.71
    imeo
    -0.71
    picking
    -0.70
    pour
    -0.70
    é¾į
    -0.68
    chat
    -0.65
    using
    -0.65
    clair
    -0.65
    bard
    -0.64
    xtap
    -0.64
    POSITIVE LOGITS
     ones
    0.67
     Razor
    0.65
     fug
    0.63
     humanoid
    0.63
     silhou
    0.61
     cardboard
    0.61
     creatures
    0.61
     device
    0.60
     moniker
    0.60
     creature
    0.60
    Activations Density 9.086%

    No Known Activations