© 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. 39905
    Prev
    Next
    INDEX
    Explanations

    technical terms and details related to programming languages and technologies

    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
    +0.21
    1.0%
    386
    +0.10
    0.5%
    706
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.21
    0.23
    119
    +0.10
    0.10
    640
    +0.10
    0.20
    Negative Logits
    oute
    -0.77
    rament
    -0.71
     reload
    -0.67
     bluff
    -0.66
    inently
    -0.65
    avorite
    -0.63
    inally
    -0.63
    ilage
    -0.60
    incinn
    -0.60
    inately
    -0.60
    POSITIVE LOGITS
    WARD
    0.71
    fare
    0.71
    finding
    0.70
     reminiscent
    0.69
    hered
    0.67
    abl
    0.66
     Affect
    0.66
     resembling
    0.66
     resembles
    0.66
    LI
    0.66
    Activations Density 10.530%

    No Known Activations