© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 33116
    Prev
    Next
    INDEX
    Explanations

    words related to imitation or copying

    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%
    255
    +0.15
    0.7%
    541
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.20
    0.11
    362
    +0.15
    0.10
    271
    +0.12
    0.04
    Negative Logits
    starter
    -0.70
    band
    -0.70
    Series
    -0.69
    rich
    -0.69
    endale
    -0.68
    omen
    -0.67
    bard
    -0.67
    nut
    -0.67
    Plus
    -0.66
    ãĥģ
    -0.65
    POSITIVE LOGITS
    lihood
    0.94
     likeness
    0.84
     imitate
    0.79
     mimic
    0.78
     mim
    0.77
    iliar
    0.77
     imitation
    0.73
     emulate
    0.71
    imum
    0.64
    ITNESS
    0.64
    Activations Density 9.271%

    No Known Activations