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. 10-RES-JB
    6. 20844
    Prev
    Next
    INDEX
    Explanations

    words related to discussions, debates, and assertions

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to questions, concerns, and emotional responses in a societal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     *.
    -0.77
    urations
    -0.70
     Helpful
    -0.68
    ":["
    -0.65
     ItemLevel
    -0.64
     supra
    -0.64
    .","
    -0.64
     Conduct
    -0.63
     Anon
    -0.62
    .$
    -0.62
    POSITIVE LOGITS
    less
    1.07
    iest
    0.95
    ocratic
    0.91
    packed
    0.87
    grab
    0.86
    lessly
    0.84
    -
    0.84
    Balt
    0.82
    reader
    0.78
    ariat
    0.77
    Activations Density 0.451%

    No Known Activations