© 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. 34764
    Prev
    Next
    INDEX
    Explanations

    words related to actions and behaviors

    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
    434
    +0.01
    0.5%
    166
    +0.01
    0.5%
    124
    +0.01
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.01
    0.39
    393
    +0.01
    0.33
    64
    +0.01
    -0.25
    Negative Logits
    SHARE
    -0.11
    natureconservancy
    -0.10
     caption
    -0.09
    Operation
    -0.09
    uble
    -0.09
     Jr
    -0.09
    ACTED
    -0.09
     MISS
    -0.09
     Hood
    -0.08
     buttons
    -0.08
    POSITIVE LOGITS
    £ı
    0.13
    ©¶æ
    0.12
    ¼
    0.11
    yip
    0.11
    sembly
    0.11
    RNA
    0.10
     confir
    0.10
     metic
    0.10
    unal
    0.09
    advertising
    0.09
    Activations Density 12.169%

    No Known Activations