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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 10811
    Prev
    Next
    INDEX
    Explanations

    large numerical figures

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     grate
    -0.59
     whiff
    -0.57
    leans
    -0.55
     Else
    -0.54
     Abram
    -0.54
     slightest
    -0.54
     experiment
    -0.53
     Seal
    -0.53
     microsc
    -0.53
     Pros
    -0.53
    POSITIVE LOGITS
    %.
    0.80
    bps
    0.73
    %;
    0.72
    ãĥĩãĤ£
    0.71
    fps
    0.69
    %,
    0.68
     destinations
    0.68
    livion
    0.67
    ãĥ¯ãĥ³
    0.66
    EStreamFrame
    0.65
    Activations Density 0.175%

    No Known Activations