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

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 12721
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person named "Huntsman" in different contexts and scenarios

    oai_token-act-pair · gpt-3.5-turbo

    the name "Huntsman" or related terms referring to Huntsman

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Diego
    -0.74
     dh
    -0.72
     partition
    -0.71
    Disk
    -0.70
    ilipp
    -0.69
    Äĩ
    -0.69
    Angelo
    -0.67
    addy
    -0.67
    eco
    -0.67
     ip
    -0.67
    POSITIVE LOGITS
     Hunts
    4.33
    Hun
    1.88
     hunts
    1.67
     Hunt
    1.57
     Hunters
    1.44
    Hunt
    1.31
     Birmingham
    1.30
     Hoover
    1.27
     Anchorage
    1.20
     Hunting
    1.15
    Activations Density 0.021%

    No Known Activations