© 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. 5143
    Prev
    Next
    INDEX
    Explanations

    mentions of 32-bit and 64-bit technology

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "bit" in various contexts related to computing

    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
     oun
    -0.78
    ammad
    -0.77
    rouse
    -0.75
    inarily
    -0.73
    ammed
    -0.71
    ¥µ
    -0.71
    ateful
    -0.71
    pez
    -0.68
     Siber
    -0.68
    lished
    -0.66
    POSITIVE LOGITS
    coins
    1.08
    terness
    0.99
    buck
    0.92
    bit
    0.90
    ertodd
    0.80
    ching
    0.76
    mask
    0.74
    tery
    0.74
    bite
    0.74
    cham
    0.71
    Activations Density 0.006%

    No Known Activations