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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 650
    Prev
    Next
    INDEX
    Explanations

    measurements in meters or feet

    oai_token-act-pair · gpt-3.5-turbo

    mentions of length measurements, often in inches, feet, miles, km, or metres.

    oai_token-act-pair · gemini-2.0-flashTriggered by @mattgrace134
    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
    •Numeric Features
    •Features About Measurement

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    711
    +0.14
    0.4%
    564
    +0.13
    0.4%
    59
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    35
    +0.14
    0.05
    678
    +0.13
    0.05
    99
    +0.13
    0.05
    Negative Logits
     Peb
    -0.99
    asso
    -0.98
     Nile
    -0.96
    uld
    -0.95
    YN
    -0.94
    icent
    -0.94
    fed
    -0.92
    ebook
    -0.91
    ulations
    -0.91
     Ig
    -0.91
    POSITIVE LOGITS
     diameter
    1.23
    iameter
    1.16
     radius
    1.11
     (~
    1.11
     circumference
    1.05
     bonded
    1.04
     apiece
    1.01
     conflic
    1.00
     increments
    1.00
     displacement
    0.95
    Activations Density 0.886%

    No Known Activations