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. 8-RES-JB
    6. 8856
    Prev
    Next
    INDEX
    Explanations

    mention drum-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to drums and drumming in music-related contexts

    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
     Tasman
    -0.73
     Mandela
    -0.68
     Pref
    -0.65
     Agency
    -0.65
    hiro
    -0.64
     Upton
    -0.64
     coron
    -0.63
    ################
    -0.62
     Morales
    -0.60
     Kiw
    -0.60
    POSITIVE LOGITS
    mers
    1.43
    ming
    1.27
    sonian
    1.08
    sticks
    1.05
    nas
    1.05
    mond
    1.00
    beat
    0.99
    stick
    0.95
    lins
    0.93
    staff
    0.91
    Activations Density 0.037%

    No Known Activations