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. 4-RES-JB
    6. 14981
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to specific individuals named Claude

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Claude" and its variations in the text

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

    No Comments

    Negative Logits
    WARD
    -0.88
    BALL
    -0.78
    IED
    -0.75
    NOR
    -0.72
    watch
    -0.71
    lake
    -0.71
    shine
    -0.70
    spot
    -0.69
    ä
    -0.68
    spin
    -0.68
    POSITIVE LOGITS
    Cla
    1.08
    ignt
    0.89
    ussen
    0.89
    ftime
    0.85
    uty
    0.84
     Claude
    0.84
    issance
    0.83
    utes
    0.82
    fters
    0.82
     Cla
    0.80
    Activations Density 0.013%

    No Known Activations