© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 70
    Prev
    Next
    INDEX
    Explanations

    specific programming code patterns and configurations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    640
    +0.16
    0.6%
    447
    +0.16
    0.6%
    393
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.16
    0.07
    289
    +0.16
    0.03
    160
    +0.15
    0.09
    Negative Logits
    theless
    -1.16
     mathemat
    -0.94
     experien
    -0.94
    ngth
    -0.94
    Ò
    -0.92
    ensibly
    -0.90
     obser
    -0.89
    emaker
    -0.87
     proactive
    -0.86
    cients
    -0.86
    POSITIVE LOGITS
     */
    1.12
    src
    1.03
    html
    1.03
    $$
    1.01
    __
    1.01
    "},
    0.99
     \
    0.99
    )))
    0.98
    */
    0.97
     respectively
    0.97
    Activations Density 0.758%

    No Known Activations