© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7365
    Prev
    Next
    INDEX
    Explanations

    names of individuals who have served in various professional capacities

    oai_token-act-pair · gpt-3.5-turbo

    individuals and their roles or positions of authority

    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
    llers
    -0.67
     strangers
    -0.65
     learners
    -0.64
    isphere
    -0.64
     passer
    -0.64
    rained
    -0.63
     passers
    -0.62
     bandwagon
    -0.62
    Tickets
    -0.62
    Methods
    -0.62
    POSITIVE LOGITS
     Nixon
    0.99
     administrations
    0.98
     Vice
    0.92
     deputy
    0.92
     Watergate
    0.92
     Deputy
    0.91
     Treasury
    0.91
    utenant
    0.89
     Reagan
    0.89
     counsel
    0.89
    Activations Density 0.315%

    No Known Activations