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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 21467
    Prev
    Next
    INDEX
    Explanations

    definitions or actions related to the word "bust."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "bust" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    velength
    -0.83
    THER
    -0.73
     vomit
    -0.69
     Rouge
    -0.69
    nsic
    -0.69
    termination
    -0.68
    esthetic
    -0.66
    WAYS
    -0.66
    perse
    -0.66
    asonable
    -0.65
    POSITIVE LOGITS
     bust
    1.14
     Bust
    0.95
    endor
    0.87
    buster
    0.86
    enance
    0.85
    outs
    0.85
    sd
    0.83
    neck
    0.82
    aign
    0.81
    s
    0.81
    Activations Density 0.013%

    No Known Activations