© 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. 45871
    Prev
    Next
    INDEX
    Explanations

    specific details related to time, duration, and events happening within specific time frames

    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
    238
    +0.08
    0.5%
    158
    +0.07
    0.4%
    520
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.08
    0.14
    649
    +0.07
    0.04
    426
    +0.07
    0.07
    Negative Logits
     contrace
    -0.55
    umbn
    -0.55
    fortune
    -0.51
    earchers
    -0.50
    umblr
    -0.49
    culosis
    -0.49
    ########
    -0.49
     sorts
    -0.48
    apons
    -0.48
    affer
    -0.48
    POSITIVE LOGITS
     increments
    0.77
     apiece
    0.77
     Ago
    0.62
     ago
    0.61
    iversary
    0.57
    cake
    0.54
    undred
    0.54
    SCP
    0.53
    duration
    0.52
    inventoryQuantity
    0.51
    Activations Density 6.903%

    No Known Activations