© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 8531
    Prev
    Next
    INDEX
    Explanations

    images made up of various symbols forming shapes

    oai_token-act-pair · gpt-3.5-turbo

    patterns of punctuation and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     endors
    -0.79
     retrospective
    -0.73
     advisory
    -0.72
     sponsor
    -0.72
     presentations
    -0.70
     presentation
    -0.69
    hement
    -0.69
     presenter
    -0.69
     prospect
    -0.68
     embargo
    -0.68
    POSITIVE LOGITS
    $$
    1.15
    \\
    1.12
    -|
    1.11
    ||
    1.09
    Î
    1.08
    ^{
    1.06
    -.
    1.05
    {\
    1.03
    É
    1.02
    ^
    1.02
    Activations Density 0.110%

    No Known Activations