© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 13116
    Prev
    Next
    INDEX
    Explanations

    phrases related to declarations or statements

    oai_token-act-pair · gpt-3.5-turbo

    references to declarations and related formal statements

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ROR
    -0.75
     Sins
    -0.68
    iday
    -0.65
    isson
    -0.64
     Insider
    -0.63
    itably
    -0.63
    ATA
    -0.62
    African
    -0.61
    committee
    -0.61
    bal
    -0.60
    POSITIVE LOGITS
    aration
    1.11
    arations
    1.04
    ignty
    0.87
    arat
    0.76
     declaration
    0.76
    ension
    0.76
    prints
    0.75
    arant
    0.74
    otle
    0.72
     Decl
    0.70
    Activations Density 0.076%

    No Known Activations