© 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 EvalsExportsinterp-engineNEWAPI 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. 1-RES-JB
    11. 5725
    Prev
    Next
    INDEX
    Explanations

    references to specific characters, specifically "Raven" and "Hawk"

    oai_token-act-pair · gpt-3.5-turbo

    Proper nouns related to characters or entities named Raven and Hawk

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    perature
    -0.88
    ablishment
    -0.86
    awaru
    -0.75
    undo
    -0.71
    oji
    -0.69
     Cuomo
    -0.69
     Pradesh
    -0.69
    aleb
    -0.68
    Þ
    -0.67
    porary
    -0.67
    POSITIVE LOGITS
    claw
    1.26
     Raven
    1.23
    hawk
    1.19
    hound
    1.17
    Raven
    1.11
    crow
    1.05
    bird
    1.00
    bolt
    0.92
    flame
    0.91
    naissance
    0.90
    Activations Density 0.017%

    No Known Activations