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. 3-RES-JB
    6. 22268
    Prev
    Next
    INDEX
    Explanations

    phrases related to film or video credits

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "credits."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ife
    -0.76
    stros
    -0.68
    angular
    -0.67
    ISH
    -0.66
     advers
    -0.65
    oret
    -0.62
    othes
    -0.62
    IFE
    -0.62
     snail
    -0.61
    emort
    -0.61
    POSITIVE LOGITS
     Credits
    1.13
     credits
    1.09
    Credits
    0.92
    olor
    0.82
    urden
    0.78
    Footnote
    0.78
    heet
    0.77
    redited
    0.77
    ounters
    0.76
    ittal
    0.76
    Activations Density 0.006%

    No Known Activations