Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 13962
    Prev
    Next
    INDEX
    Explanations

    occurrences of dates and time-related expressions

    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
    174
    +0.16
    0.5%
    393
    +0.16
    0.5%
    30
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    706
    +0.16
    0.07
    30
    +0.16
    0.05
    504
    +0.14
    0.06
    Negative Logits
    enegger
    -1.46
    renheit
    -1.13
    gur
    -1.04
    idan
    -1.04
    alore
    -1.03
    kaya
    -1.00
    emale
    -1.00
    è£ħ
    -0.99
    iasis
    -0.97
    jri
    -0.96
    POSITIVE LOGITS
     exactly
    1.16
    soever
    1.13
    abouts
    1.00
     exact
    1.00
    assetsadobe
    0.98
     confir
    0.98
    ewitness
    0.95
     livest
    0.95
     prompted
    0.91
     awaited
    0.91
    Activations Density 0.975%

    No Known Activations