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. 7-RES-JB
    6. 18242
    Prev
    Next
    INDEX
    Explanations

    terms related to computer programming or file formatting

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number 8 and 9 in numerical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aging
    -0.63
    isconsin
    -0.61
    atis
    -0.61
    meaning
    -0.61
     ric
    -0.59
    uno
    -0.59
    cat
    -0.58
    uly
    -0.58
    cius
    -0.58
     Richards
    -0.58
    POSITIVE LOGITS
    pmwiki
    0.78
    Dialogue
    0.75
    âĵĺ
    0.72
    VERTISEMENT
    0.70
    Quotes
    0.69
    Appearances
    0.68
    Catalog
    0.66
    Trivia
    0.65
    Ü
    0.65
    ?????-
    0.63
    Activations Density 0.304%

    No Known Activations