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. 19011
    Prev
    Next
    INDEX
    Explanations

    phrases related to the importance or function of different concepts or systems

    oai_token-act-pair · gpt-3.5-turbo

    key concepts related to systems, roles, and influences 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
     largeDownload
    -0.69
     Delicious
    -0.62
    oops
    -0.59
    ģ«
    -0.57
    outed
    -0.55
    then
    -0.55
    yx
    -0.55
    anos
    -0.55
     fru
    -0.54
     furiously
    -0.54
    POSITIVE LOGITS
     versus
    1.03
     among
    0.96
     amongst
    0.95
     outweigh
    0.87
     throughout
    0.81
     against
    0.81
     amidst
    0.80
     in
    0.80
     during
    0.80
    Footnote
    0.78
    Activations Density 0.367%

    No Known Activations