© 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
    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. 3365
    Prev
    Next
    INDEX
    Explanations

    detailed technical information related to biological experiments and analysis

    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
    447
    +0.20
    0.8%
    436
    +0.12
    0.5%
    611
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.20
    0.03
    296
    +0.12
    0.02
    394
    +0.12
    0.02
    Negative Logits
    fw
    -0.93
    kees
    -0.85
    izers
    -0.85
    gets
    -0.84
    esses
    -0.84
    izer
    -0.82
    lance
    -0.81
    unts
    -0.79
    vale
    -0.76
    bern
    -0.76
    POSITIVE LOGITS
     Brief
    0.78
     largeDownload
    0.76
     Gutenberg
    0.73
     Di
    0.72
     Cause
    0.69
     Reconstruction
    0.69
     Moroc
    0.68
    ufact
    0.68
     subsistence
    0.66
     COVER
    0.64
    Activations Density 0.122%

    No Known Activations