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. 8-RES-JB
    6. 22100
    Prev
    Next
    INDEX
    Explanations

    names of movie characters

    oai_token-act-pair · gpt-3.5-turbo

    notable roles played by actors in film and television

    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
     VIDEOS
    -0.92
    BOOK
    -0.71
     newsletters
    -0.71
    INFO
    -0.70
     blogging
    -0.70
    merce
    -0.69
     hindsight
    -0.67
    LEASE
    -0.66
     testimonies
    -0.66
    CHAT
    -0.65
    POSITIVE LOGITS
     protagonist
    0.85
     Finch
    0.84
     Spock
    0.82
     Weasley
    0.81
     Joker
    0.81
     vigilante
    0.78
     Grimm
    0.77
     Uz
    0.76
     Scully
    0.75
     heroine
    0.75
    Activations Density 0.383%

    No Known Activations