© 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. 13709
    Prev
    Next
    INDEX
    Explanations

    instances where the phrase "of all" appears

    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
    651
    +0.04
    0.5%
    373
    +0.04
    0.5%
    384
    +0.04
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.04
    -0.00
    307
    +0.04
    0.02
    569
    +0.04
    0.02
    Negative Logits
     incre
    -0.29
     Pwr
    -0.28
    forth
    -0.28
     quo
    -0.28
     hurd
    -0.28
     awa
    -0.27
    ilee
    -0.27
     caution
    -0.27
     abdom
    -0.26
    ascript
    -0.26
    POSITIVE LOGITS
    arts
    0.30
    items
    0.28
    ategories
    0.28
     Categories
    0.28
     Heroes
    0.27
    agram
    0.26
     competitions
    0.26
    Items
    0.26
    zzi
    0.26
    arding
    0.25
    Activations Density 0.035%

    No Known Activations