© 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. 34711
    Prev
    Next
    INDEX
    Explanations

    text related to computer programming, technical instructions, and dialog boxes

    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%
    679
    +0.11
    0.5%
    289
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.21
    0.21
    288
    +0.11
    0.20
    575
    +0.09
    0.14
    Negative Logits
    ulz
    -0.80
    rolet
    -0.79
    isher
    -0.79
    noon
    -0.77
    shots
    -0.72
    gun
    -0.72
    arah
    -0.70
    urst
    -0.69
    fall
    -0.69
    innon
    -0.68
    POSITIVE LOGITS
     dialogue
    1.00
    ues
    0.88
    naire
    0.82
     dialog
    0.80
     Dialogue
    0.80
    ogue
    0.72
     negotiation
    0.71
     Franç
    0.69
     reperto
    0.69
     theatre
    0.69
    Activations Density 7.494%

    No Known Activations