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. 7-RES-JB
    6. 20211
    Prev
    Next
    INDEX
    Explanations

    mentions of professions or roles within a social context

    oai_token-act-pair · gpt-3.5-turbo

    references to specific professions or roles, particularly in a context involving social or historical themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¥ŀ
    -0.76
    illegal
    -0.71
    ourcing
    -0.71
    chwitz
    -0.70
    sembly
    -0.70
    edIn
    -0.70
    izoph
    -0.70
    andise
    -0.69
    fml
    -0.69
    ugar
    -0.68
    POSITIVE LOGITS
     extraord
    0.94
    osphere
    0.85
     who
    0.80
    liest
    0.78
     archetype
    0.77
    iest
    0.75
     monk
    0.74
    agonist
    0.73
    hood
    0.73
     Ernest
    0.73
    Activations Density 0.387%

    No Known Activations