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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 6-RES-JB
    6. 14349
    Prev
    Next
    INDEX
    Explanations

    words related to decisions being made

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "made"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sit
    -0.69
     ding
    -0.66
     decaying
    -0.66
     rotting
    -0.61
     stripes
    -0.60
     peppers
    -0.58
     bos
    -0.58
     wit
    -0.58
     grou
    -0.57
     striped
    -0.57
    POSITIVE LOGITS
    emort
    0.94
     sure
    0.86
    ensibly
    0.82
    gements
    0.79
    itives
    0.78
    urate
    0.78
    ezvous
    0.77
    awaru
    0.76
    oji
    0.76
    vious
    0.76
    Activations Density 0.045%

    No Known Activations