Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 17430
    Prev
    Next
    INDEX
    Explanations

    common expressions using the word "bit" to convey a small amount or degree

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference the concept of "a bit."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andise
    -0.73
    neum
    -0.72
    lords
    -0.70
    sole
    -0.70
    atu
    -0.70
    avers
    -0.69
    ordon
    -0.68
    .–
    -0.67
    thood
    -0.66
    olina
    -0.62
    POSITIVE LOGITS
     bit
    3.53
    bit
    2.07
     bits
    1.91
     tad
    1.89
     BIT
    1.78
     Bit
    1.68
    Bit
    1.67
    BIT
    1.55
     little
    1.46
     Bits
    1.44
    Activations Density 0.026%

    No Known Activations