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. 7458
    Prev
    Next
    INDEX
    Explanations

    keywords related to data and software development

    oai_token-act-pair · gpt-3.5-turbo

    references to media and image-related content

    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
    ciplinary
    -0.76
    Ń·
    -0.67
    ¥ŀ
    -0.65
    Lear
    -0.63
    ensibly
    -0.63
     carbohyd
    -0.63
    rank
    -0.62
    ãĥ¼ãĥĨãĤ£
    -0.61
    direction
    -0.61
    pill
    -0.61
    POSITIVE LOGITS
     =================================
    1.02
     TOTAL
    0.96
     ----------------------------------------------------------------
    0.94
     Submit
    0.92
     Miscellaneous
    0.90
    <|endoftext|>
    0.90
     Discuss
    0.85
     Leilan
    0.85
     Others
    0.83
     Overall
    0.83
    Activations Density 0.149%

    No Known Activations