© 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. 3-RES-JB
    11. 20105
    Prev
    Next
    INDEX
    Explanations

    names of people or places, possibly related to a specific topic

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, especially names and locations

    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
    Arab
    -0.68
    apult
    -0.67
    AAF
    -0.60
    qqa
    -0.59
    zig
    -0.59
    QUI
    -0.59
     Antar
    -0.58
    berman
    -0.58
    cule
    -0.58
    abase
    -0.57
    POSITIVE LOGITS
     Griffith
    1.00
    s
    0.87
    shire
    0.86
    saf
    0.83
    icides
    0.81
    milo
    0.81
    guards
    0.79
    cale
    0.78
    enhagen
    0.77
     hon
    0.76
    Activations Density 0.015%

    No Known Activations