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. 18003
    Prev
    Next
    INDEX
    Explanations

    words related to personal hygiene and grooming, specifically items like razors, toothpaste, and soap

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals named "Jazmine" or similar variants

    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
     Seah
    -0.66
     Fargo
    -0.64
     foremost
    -0.64
     Impossible
    -0.64
     Kraken
    -0.64
    ãĤ©
    -0.63
     Kepler
    -0.63
     Carolina
    -0.61
    nces
    -0.60
    perature
    -0.60
    POSITIVE LOGITS
    ombie
    1.10
    hou
    1.09
    hang
    0.99
    awa
    0.93
    illion
    0.91
    quez
    0.91
     Sharif
    0.91
    eez
    0.91
    ahar
    0.90
    ahn
    0.87
    Activations Density 0.020%

    No Known Activations