© 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. 15555
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "bit" at different activation levels

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "bit"

    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
    inarily
    -0.70
    stice
    -0.69
    authorized
    -0.66
    ateful
    -0.63
    inate
    -0.63
    ammad
    -0.63
    yout
    -0.62
     Oath
    -0.62
    ortium
    -0.61
    taining
    -0.60
    POSITIVE LOGITS
    umen
    0.89
    terness
    0.83
    buck
    0.83
    umin
    0.80
    chery
    0.80
    ches
    0.71
    wig
    0.71
     bit
    0.70
    maps
    0.67
    cone
    0.66
    Activations Density 0.020%

    No Known Activations