© 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. 17235
    Prev
    Next
    INDEX
    Explanations

    statements containing mentions of specific terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of omissions or absences in documents

    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
    ecast
    -0.76
    steam
    -0.73
    "},"
    -0.71
    ienced
    -0.71
    agues
    -0.70
    profit
    -0.69
    SAN
    -0.69
    Experience
    -0.69
    Emer
    -0.68
    Demand
    -0.67
    POSITIVE LOGITS
     quotes
    1.33
     passages
    1.30
     mentions
    1.30
     references
    1.29
     paragraphs
    1.24
     footnote
    1.22
     mention
    1.21
     excerpt
    1.17
     paragraph
    1.17
     excerpts
    1.12
    Activations Density 1.526%

    No Known Activations