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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 22387
    Prev
    Next
    INDEX
    Explanations

    information about individuals and organizations involved in various projects or businesses

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to people or organizations involved in various activities

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    adesh
    -0.83
    ghazi
    -0.82
    worthiness
    -0.80
    verage
    -0.77
    condition
    -0.76
    fax
    -0.72
    thood
    -0.71
    ukong
    -0.69
    ogging
    -0.68
    blems
    -0.68
    POSITIVE LOGITS
     consortium
    0.87
     Marcel
    0.82
     collaborator
    0.79
     Architects
    0.76
     pseudonym
    0.76
     visionary
    0.76
     collaborators
    0.75
     renowned
    0.74
     Shap
    0.74
     Birch
    0.73
    Activations Density 0.566%

    No Known Activations