© 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. 6103
    Prev
    Next
    INDEX
    Explanations

    questions about physical attributes, characteristics, or details

    oai_token-act-pair · gpt-3.5-turbo

    inquiries regarding physical characteristics and comparisons

    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
    irit
    -0.86
    iscovery
    -0.83
    Future
    -0.81
    comings
    -0.79
    gression
    -0.77
    aughs
    -0.76
    Community
    -0.75
    isode
    -0.73
    reality
    -0.72
    annis
    -0.71
    POSITIVE LOGITS
     spaced
    0.95
     towed
    0.89
     punct
    0.88
     irrig
    0.85
     humidity
    0.85
     spacing
    0.84
     piping
    0.84
     waterproof
    0.83
     weld
    0.82
     thickness
    0.82
    Activations Density 0.632%

    No Known Activations