© 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. 10-RES-JB
    11. 12046
    Prev
    Next
    INDEX
    Explanations

    expressions related to change or transformation

    oai_token-act-pair · gpt-3.5-turbo
    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
    ety
    -0.71
    tumblr
    -0.68
     anecd
    -0.68
    ital
    -0.68
    via
    -0.66
     PLUS
    -0.65
    ivals
    -0.64
    xual
    -0.63
    iga
    -0.62
    outine
    -0.62
    POSITIVE LOGITS
     swung
    0.91
     swinging
    0.83
     tipping
    0.81
    inning
    0.78
    hatt
    0.76
     peeled
    0.75
     bowed
    0.75
    ayers
    0.73
     tightening
    0.73
    urned
    0.73
    Activations Density 0.227%

    No Known Activations