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. 7237
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, specifically those related to the name "Palmer"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Palmer."

    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
     quot
    -0.72
    REE
    -0.71
    allow
    -0.71
    heet
    -0.70
    err
    -0.68
    aspx
    -0.67
    outer
    -0.66
    ctx
    -0.65
    URI
    -0.65
     CLSID
    -0.64
    POSITIVE LOGITS
    ston
    1.19
     Palmer
    0.95
    icum
    0.80
    mares
    0.78
    ertodd
    0.75
    der
    0.75
    stein
    0.75
    ragon
    0.73
    yss
    0.73
    gren
    0.72
    Activations Density 0.007%

    No Known Activations