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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 14721
    Prev
    Next
    INDEX
    Explanations

    references to the name "Hunter"

    oai_token-act-pair · gpt-3.5-turbo

    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 @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raints
    -1.00
    ible
    -0.79
    orship
    -0.79
    itutional
    -0.78
    iment
    -0.77
    onent
    -0.73
    ications
    -0.72
    eas
    -0.71
    ruction
    -0.71
    ations
    -0.70
    POSITIVE LOGITS
     Hunter
    0.92
    sonian
    0.90
    hunter
    0.80
    Hunter
    0.80
     hunter
    0.79
    stown
    0.76
    gon
    0.75
    stal
    0.74
    ãĥ£
    0.74
    son
    0.74
    Activations Density 0.010%

    No Known Activations