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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-RES-JB
    6. 21481
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names, especially "Burr" and "Pebble 2."

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual or brand, particularly "Burr" and "Pebble."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    e
    -0.79
     Liberia
    -0.70
    gaard
    -0.70
    ories
    -0.69
    nda
    -0.66
    EEE
    -0.66
    onym
    -0.66
    ////////////////
    -0.65
    Kin
    -0.63
    llo
    -0.63
    POSITIVE LOGITS
    arov
    0.97
    abba
    0.82
    oola
    0.81
    iceps
    0.79
    abies
    0.79
    itton
    0.78
    ski
    0.78
    ategory
    0.76
    agus
    0.76
    rypt
    0.76
    Activations Density 0.011%

    No Known Activations