© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13294
    Prev
    Next
    INDEX
    Explanations

    technical language and code snippets related to programming and software development

    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
    709
    +0.14
    0.5%
    254
    +0.12
    0.4%
    655
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    655
    +0.14
    0.06
    429
    +0.12
    0.03
    582
    +0.12
    0.03
    Negative Logits
     lifes
    -0.86
    odies
    -0.86
    enium
    -0.85
    illes
    -0.82
    senal
    -0.78
     scept
    -0.77
    rawdownloadcloneembedreportprint
    -0.77
     lif
    -0.77
    endar
    -0.76
    obal
    -0.76
    POSITIVE LOGITS
    -)
    1.00
     namely
    0.97
    typically
    0.95
    insert
    0.92
    although
    0.92
    construct
    0.90
     eg
    0.86
    %)
    0.86
    small
    0.83
    upper
    0.82
    Activations Density 0.386%

    No Known Activations