© 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. 4-RES-JB
    11. 10408
    Prev
    Next
    INDEX
    Explanations

    phrases indicating satisfaction or pleasure in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    expressions of satisfaction or approval

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

    No Comments

    Negative Logits
    sites
    -0.74
    chin
    -0.73
    mouth
    -0.69
    hops
    -0.69
     teasp
    -0.69
     <@
    -0.67
     GOODMAN
    -0.67
    fighter
    -0.66
    mite
    -0.64
    fair
    -0.63
    POSITIVE LOGITS
     regards
    1.38
     regard
    1.19
    stood
    1.05
    standing
    1.03
     respect
    0.97
     impunity
    0.93
    draw
    0.81
    drawn
    0.79
     dignity
    0.78
     utmost
    0.72
    Activations Density 0.096%

    No Known Activations