© 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. 10-RES-JB
    11. 11161
    Prev
    Next
    INDEX
    Explanations

    topic-specific references and brand names

    oai_token-act-pair · gpt-3.5-turbo

    specific references to influential individuals, brands, and titles in the context of media or entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ":"","
    -0.79
     |--
    -0.73
    .}
    -0.72
    :{
    -0.71
    }.
    -0.69
    `,
    -0.68
    \.
    -0.68
    .ãĢį
    -0.67
     [];
    -0.66
    ''.
    -0.63
    POSITIVE LOGITS
     into
    0.90
     onto
    0.81
     alive
    0.77
     afloat
    0.76
     accountable
    0.72
     away
    0.66
     squarely
    0.63
     shine
    0.62
     closer
    0.62
     obsolete
    0.62
    Activations Density 0.559%

    No Known Activations