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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 4479
    Prev
    Next
    INDEX
    Explanations

    mentions of vocal abilities or performers

    oai_token-act-pair · gpt-3.5-turbo

    references to vocal abilities or vocal characteristics

    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
    agher
    -0.90
     Reincarn
    -0.89
    uden
    -0.83
    roxy
    -0.73
    ionage
    -0.71
     Carbuncle
    -0.71
     Peb
    -0.70
    awaru
    -0.70
     Journals
    -0.70
    RAG
    -0.69
    POSITIVE LOGITS
    izations
    1.19
     cords
    1.15
    isations
    1.11
     chords
    1.11
    izers
    1.03
    ized
    0.99
    izing
    0.99
    izer
    0.97
    izes
    0.96
     vocal
    0.94
    Activations Density 0.019%

    No Known Activations