© 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. 8-RES-JB
    11. 3851
    Prev
    Next
    INDEX
    Explanations

    names of individuals or teams involved in competitions or matches

    oai_token-act-pair · gpt-3.5-turbo

    instances of competitive matchups or events

    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
    Reviewer
    -0.88
     "$:/
    -0.75
    nces
    -0.73
    naissance
    -0.71
    ulously
    -0.68
     depreciation
    -0.66
    cipline
    -0.63
    iom
    -0.62
    ibrary
    -0.62
    tymology
    -0.61
    POSITIVE LOGITS
     Comparison
    0.80
     Ratio
    0.78
     [*]
    0.69
    frac
    0.64
     respectively
    0.64
    ?????
    0.64
     Unlimited
    0.63
     LLP
    0.62
     Difference
    0.62
     Testing
    0.62
    Activations Density 0.216%

    No Known Activations