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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 8-RES-JB
    6. 3639
    Prev
    Next
    INDEX
    Explanations

    words related to delicate sensations or experiences

    oai_token-act-pair · gpt-3.5-turbo

    references to delicacy and medicinal usage, particularly related to food and substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elsen
    -0.76
    idem
    -0.71
    quickShipAvailable
    -0.67
    eret
    -0.65
    fire
    -0.65
    avez
    -0.63
    jamin
    -0.62
    leigh
    -0.61
    IGH
    -0.60
     Dayton
    -0.60
    POSITIVE LOGITS
    natureconservancy
    0.80
    ately
    0.79
    encies
    0.78
    tis
    0.76
     ammon
    0.72
    ente
    0.70
    orically
    0.70
    assium
    0.68
    ency
    0.68
     cer
    0.68
    Activations Density 0.111%

    No Known Activations