© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 20599
    Prev
    Next
    INDEX
    Explanations

    comparisons or instances where one thing is exceeding another in quantity or quality

    oai_token-act-pair · gpt-3.5-turbo

    terms related to exceeding or surpassing thresholds or records

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     loc
    -0.63
    ogy
    -0.62
    area
    -0.62
    amide
    -0.61
     ACTIONS
    -0.59
    alian
    -0.59
    olson
    -0.57
     COURT
    -0.57
    Mesh
    -0.57
    hart
    -0.56
    POSITIVE LOGITS
     surpass
    0.93
     surpassed
    0.86
     eclips
    0.85
    manship
    0.79
    ceed
    0.78
    peak
    0.71
    cedes
    0.70
    =>
    0.70
    riet
    0.69
    racuse
    0.68
    Activations Density 0.023%

    No Known Activations