Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 15182
    Prev
    Next
    INDEX
    Explanations

    numbers and technical terms

    oai_token-act-pair · gpt-3.5-turbo

    references to differences and comparisons in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     respectively
    -0.80
    Anyway
    -0.58
     Chak
    -0.56
     etc
    -0.56
     Kush
    -0.56
     Jung
    -0.54
     Kiw
    -0.53
     Optimus
    -0.53
     NZ
    -0.52
     apiece
    -0.52
    POSITIVE LOGITS
    âĢ
    0.79
    ãĤ¼ãĤ¦ãĤ¹
    0.76
    ãĢ
    0.73
    ãĥīãĥ©
    0.64
    advertisement
    0.63
    \",
    0.63
    ãĤ©
    0.63
    ãĥ´ãĤ¡
    0.62
    ¯¯¯¯¯¯¯¯
    0.62
     âĢ
    0.61
    Activations Density 1.296%

    No Known Activations