© 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. 3717
    Prev
    Next
    INDEX
    Explanations

    references to specific titles or names within longer texts

    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
    0.5%
    45
    +0.15
    0.5%
    760
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.16
    0.10
    739
    +0.15
    0.06
    428
    +0.14
    0.06
    Negative Logits
     arsen
    -1.13
     "@
    -1.07
    isch
    -1.02
    ittal
    -1.02
    psey
    -1.00
     roads
    -0.99
    xon
    -0.98
    pection
    -0.96
    ischer
    -0.95
     postal
    -0.93
    POSITIVE LOGITS
     Remastered
    1.57
     Volume
    1.28
    feat
    1.13
    ONSORED
    1.08
     Chapter
    1.06
     [|
    1.06
     Edition
    1.04
     Chapters
    1.03
     Collection
    0.99
     Featuring
    0.99
    Activations Density 1.993%

    No Known Activations