© 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. 9-RES-JB
    11. 10331
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings or political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Roberts" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    liest
    -0.92
    alities
    -0.77
    lihood
    -0.74
    ascar
    -0.71
    riots
    -0.69
    mble
    -0.69
     Beir
    -0.69
    uate
    -0.66
    uated
    -0.66
    ality
    -0.65
    POSITIVE LOGITS
    haw
    1.08
    ullivan
    0.87
    eln
    0.86
    onian
    0.85
    otle
    0.82
    burgh
    0.79
    dale
    0.77
    ç·
    0.76
    DOM
    0.75
    eye
    0.75
    Activations Density 0.054%

    No Known Activations