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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 40017
    Prev
    Next
    INDEX
    Explanations

    phrases related to pretending, acting, or feigning within the context of personal experiences and fictional narratives

    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
    +0.20
    0.9%
    288
    +0.14
    0.6%
    274
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    195
    +0.20
    0.04
    274
    +0.14
    0.12
    493
    +0.13
    0.08
    Negative Logits
    âĨij
    -0.72
    cutting
    -0.68
    20439
    -0.66
    turn
    -0.65
    lean
    -0.62
    EVA
    -0.61
     GOODMAN
    -0.61
    vez
    -0.61
     srf
    -0.60
     palms
    -0.60
    POSITIVE LOGITS
     innocence
    0.82
    entious
    0.70
    ulence
    0.69
     otherwise
    0.66
     pas
    0.65
     inco
    0.64
     forgot
    0.63
     Duff
    0.62
     falsely
    0.62
    rets
    0.61
    Activations Density 8.595%

    No Known Activations