© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16337
    Prev
    Next
    INDEX
    Explanations

    expressions with the word "bit"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express a moderate degree or quantity

    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
    alsh
    -0.70
    inarily
    -0.68
     Grave
    -0.65
    itars
    -0.63
    stice
    -0.63
    taining
    -0.63
    ordan
    -0.63
    æ©
    -0.62
    inate
    -0.61
    ovies
    -0.61
    POSITIVE LOGITS
    terness
    1.04
     bit
    0.90
    buck
    0.89
    bit
    0.80
    umen
    0.76
    catentry
    0.75
    umin
    0.74
    chery
    0.72
    quart
    0.69
    mask
    0.69
    Activations Density 0.020%

    No Known Activations