© 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. 9-RES-JB
    11. 2261
    Prev
    Next
    INDEX
    Explanations

    mentions of legal or law enforcement scenarios and personal struggles

    oai_token-act-pair · gpt-3.5-turbo
    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
    Interested
    -0.76
     Contains
    -0.75
    ĸļ
    -0.69
    yip
    -0.67
    VID
    -0.65
    actionDate
    -0.65
    existent
    -0.65
     Speaking
    -0.64
    peak
    -0.63
    paren
    -0.63
    POSITIVE LOGITS
     retreated
    1.43
     reverted
    1.42
     proceeded
    1.41
     withdrew
    1.33
     promptly
    1.28
     returned
    1.27
     resorted
    1.25
     resumed
    1.23
     went
    1.22
     fled
    1.20
    Activations Density 0.430%

    No Known Activations