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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 24413
    Prev
    Next
    INDEX
    Explanations

    recommendations or suggestions being made in text

    oai_token-act-pair · gpt-3.5-turbo

    expressions of recommendations or suggestions

    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
    threat
    -0.68
    omal
    -0.65
    exist
    -0.65
    oise
    -0.63
    thia
    -0.63
    nown
    -0.62
    aptic
    -0.62
    awks
    -0.61
    istical
    -0.61
    hs
    -0.60
    POSITIVE LOGITS
     checking
    1.08
     avoiding
    1.03
     contacting
    0.93
     downloading
    0.92
     reading
    0.90
     skipping
    0.90
     purchasing
    0.89
     picking
    0.88
     keeping
    0.87
     watching
    0.87
    Activations Density 0.067%

    No Known Activations