© 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. 32369
    Prev
    Next
    INDEX
    Explanations

    descriptions of characters' appearances and clothing styles

    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
    0.7%
    500
    +0.13
    0.5%
    450
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    526
    +0.17
    -0.14
    608
    +0.13
    0.28
    762
    +0.11
    0.28
    Negative Logits
     fueled
    -0.88
     targeted
    -0.87
    Flash
    -0.87
    taboola
    -0.83
    andowski
    -0.81
     fueling
    -0.81
     Dynamics
    -0.80
    Based
    -0.80
     targeting
    -0.80
     takeaway
    -0.79
    POSITIVE LOGITS
    ,—
    1.41
     thence
    1.20
     negro
    1.14
     splend
    1.12
     consec
    1.06
     hitherto
    1.03
     Edition
    1.03
     splendid
    1.02
     labou
    1.02
     brill
    1.02
    Activations Density 38.225%

    No Known Activations