© 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. 16053
    Prev
    Next
    INDEX
    Explanations

    references to a specific person or entity named "Hunter"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the name "Hunter" in various contexts

    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
    iment
    -0.98
    ations
    -0.93
    ational
    -0.89
    ation
    -0.88
    ancies
    -0.86
    orative
    -0.85
    ible
    -0.84
    overs
    -0.82
    ating
    -0.80
    ometimes
    -0.80
    POSITIVE LOGITS
     Hunter
    0.76
     Daniels
    0.69
    hood
    0.67
    STON
    0.66
    Hunter
    0.65
    sonian
    0.65
     Davidson
    0.64
     Pence
    0.64
    bard
    0.64
    brush
    0.63
    Activations Density 0.050%

    No Known Activations