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. 5604
    Prev
    Next
    INDEX
    Explanations

    specific mentions of bodily responses, particularly related to the immune system

    oai_token-act-pair · gpt-3.5-turbo

    references to immune system responses and related physiological processes

    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
     AMERICA
    -0.73
    ãĥĩãĤ£
    -0.69
    agall
    -0.69
    raft
    -0.69
    foundland
    -0.67
    aneers
    -0.66
    holding
    -0.65
    hammer
    -0.65
    google
    -0.63
    cas
    -0.63
    POSITIVE LOGITS
     responses
    0.86
    ively
    0.81
     reperto
    0.79
     reactions
    0.79
     responsiveness
    0.79
    encies
    0.77
     response
    0.77
    ivation
    0.76
    cue
    0.75
    umph
    0.73
    Activations Density 0.037%

    No Known Activations