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. 9-RES-JB
    6. 21092
    Prev
    Next
    INDEX
    Explanations

    signal words for transitions or organizational structure indicating continuation or flow of content

    oai_token-act-pair · gpt-3.5-turbo

    the phrase indicating that an article continues further on the page

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istical
    -0.79
    ãĥ³ãĤ¸
    -0.75
    lier
    -0.70
    ICAN
    -0.67
    agnetic
    -0.65
    liest
    -0.65
    angible
    -0.64
    tre
    -0.64
    ribution
    -0.64
    mate
    -0.63
    POSITIVE LOGITS
     BELOW
    1.23
     Below
    0.97
     below
    0.95
    advertisement
    0.89
    below
    0.81
    ĸļ
    0.72
     excerpt
    0.71
    scroll
    0.71
     Reading
    0.71
     trending
    0.69
    Activations Density 0.038%

    No Known Activations