© 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. 2-RES-JB
    11. 15100
    Prev
    Next
    INDEX
    Explanations

    numbers separated by a comma and a space, specifically when the number "60" is mentioned before another number

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical values in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hammad
    -0.82
    ilater
    -0.78
    leased
    -0.77
    sem
    -0.76
    cedes
    -0.74
    onson
    -0.74
    itivity
    -0.73
     Flavoring
    -0.73
    imoto
    -0.72
    achi
    -0.72
    POSITIVE LOGITS
     Minutes
    1.22
    Hz
    0.99
     ILCS
    0.95
    625
    0.93
    60
    0.91
     Seconds
    0.90
    GW
    0.86
    70
    0.86
    61
    0.85
     Hz
    0.82
    Activations Density 0.030%

    No Known Activations