© 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. 4125
    Prev
    Next
    INDEX
    Explanations

    code syntax related terms and phrases

    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
    •Layer 6 UMAP region: Mostly-local line at bottom - local

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.28
    3.2%
    64
    +0.16
    1.9%
    481
    +0.06
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.28
    -0.08
    470
    +0.16
    0.10
    481
    +0.06
    0.28
    Negative Logits
    )."
    -0.41
    .).
    -0.38
    ]."
    -0.38
    .</
    -0.35
    .""
    -0.34
    ).[
    -0.33
    .''
    -0.33
    ."[
    -0.33
    !).
    -0.31
    .'"
    -0.31
    POSITIVE LOGITS
    ':
    0.26
    undrum
    0.25
    ibliography
    0.23
     Edit
    0.23
     FANTASY
    0.22
     Canaver
    0.22
    reenshots
    0.22
     partName
    0.21
    odore
    0.21
    prisingly
    0.21
    Activations Density 12.914%

    No Known Activations