© 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. 45749
    Prev
    Next
    INDEX
    Explanations

    names of individuals involved in a variety of situations or relationships

    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
    618
    +0.11
    0.5%
    481
    +0.11
    0.5%
    447
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.21
    326
    +0.11
    0.25
    232
    +0.11
    0.12
    Negative Logits
     locality
    -0.67
     GamerGate
    -0.56
     corrid
    -0.56
    RIP
    -0.54
     analges
    -0.53
     Sabha
    -0.53
     Anthem
    -0.52
     aromatic
    -0.52
     metic
    -0.52
     independence
    -0.52
    POSITIVE LOGITS
    lein
    0.84
    jen
    0.81
    meier
    0.70
    iewicz
    0.67
    HH
    0.65
    yk
    0.64
    enegger
    0.61
    meyer
    0.60
    equ
    0.60
    cox
    0.59
    Activations Density 9.639%

    No Known Activations