© 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. 10672
    Prev
    Next
    INDEX
    Explanations

    names of people involved in various incidents

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and terms associated with individuals involved in incidents or events

    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
    Quantity
    -0.69
    artisan
    -0.69
     unbeat
    -0.69
    optim
    -0.66
     illuminating
    -0.66
    ================================================================
    -0.65
    rising
    -0.65
    inline
    -0.64
     trillions
    -0.63
    isSpecialOrderable
    -0.63
    POSITIVE LOGITS
     pleaded
    1.34
     died
    1.26
     suffered
    1.24
     surrendered
    1.23
     suffers
    1.20
     underwent
    1.17
     escaped
    1.17
     survived
    1.09
     disappeared
    1.08
     allegedly
    1.08
    Activations Density 0.272%

    No Known Activations