© 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. 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. 4271
    Prev
    Next
    INDEX
    Explanations

    attributes or actions in a scenario

    oai_token-act-pair · gpt-3.5-turbo

    important technical specifications or conditions

    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
     promotion
    -0.84
     Opportun
    -0.77
    itism
    -0.74
     promotions
    -0.73
     persuasion
    -0.73
    href
    -0.71
     citations
    -0.71
     Promotion
    -0.70
    ivals
    -0.69
     caut
    -0.69
    POSITIVE LOGITS
     upright
    1.00
     equipped
    0.95
     sized
    0.93
     submerged
    0.93
     stationary
    0.91
     chassis
    0.91
     mechanically
    0.90
     housed
    0.90
     fitted
    0.90
     undergoing
    0.88
    Activations Density 0.651%

    No Known Activations