© 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. 20036
    Prev
    Next
    INDEX
    Explanations

    differences or unique features in comparison to others

    oai_token-act-pair · gpt-3.5-turbo

    comparisons with "other" items or entities

    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
    culosis
    -0.74
    riber
    -0.73
    ouple
    -0.72
    utenant
    -0.72
    bec
    -0.69
    ossession
    -0.69
    instead
    -0.66
    sure
    -0.65
     thanking
    -0.65
    wrong
    -0.65
    POSITIVE LOGITS
     kinds
    1.02
     types
    0.99
     forms
    0.97
     facets
    0.97
     professions
    0.96
     implementations
    0.95
     categories
    0.94
     brands
    0.93
     competitors
    0.92
     modes
    0.91
    Activations Density 0.115%

    No Known Activations