© 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. 12347
    Prev
    Next
    INDEX
    Explanations

    names or titles associated with entities or characters, specifically those related to hunting or being hunted

    oai_token-act-pair · gpt-3.5-turbo

    terms related to hunting and hunters

    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
    idency
    -0.76
    aps
    -0.71
    heses
    -0.71
     TTC
    -0.70
    Document
    -0.69
    Hamilton
    -0.68
     è£ıç
    -0.68
     CSS
    -0.68
     Consent
    -0.67
     Font
    -0.67
    POSITIVE LOGITS
     hunter
    3.71
     hunters
    3.53
     Hunters
    2.56
    hunter
    2.33
     hunting
    2.03
    Hunter
    2.00
     Hunter
    1.96
     hunts
    1.96
    hun
    1.78
     hunt
    1.76
    Activations Density 0.020%

    No Known Activations