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. 22057
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific movie franchise or character, specifically those related to the term "Apocalypse" or "Apes"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific media titles within the "Planet of the Apes" franchise

    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
     Lauder
    -0.73
    âĢ¢âĢ¢
    -0.70
    theless
    -0.68
    neck
    -0.67
     Blanc
    -0.63
    boarding
    -0.62
    utenant
    -0.61
    ï¸ı
    -0.61
    puff
    -0.60
     arsenic
    -0.60
    POSITIVE LOGITS
    artment
    1.35
    ocalyptic
    1.33
    ocalypse
    1.12
    ocaly
    1.03
    ologies
    1.02
    ologists
    1.01
    ogene
    0.97
    rax
    0.95
    ogen
    0.90
    uses
    0.89
    Activations Density 0.064%

    No Known Activations