© 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. 12076
    Prev
    Next
    INDEX
    Explanations

    numerical values that seem to represent specific data points

    oai_token-act-pair · gpt-3.5-turbo

    numerical data, particularly related to statistics and counts

    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
    anamo
    -0.52
     Aly
    -0.49
    amaru
    -0.49
    feature
    -0.49
     disadvant
    -0.49
    ramid
    -0.48
    ãĥ¼ãĥ³
    -0.47
    liga
    -0.47
    atem
    -0.47
     srf
    -0.46
    POSITIVE LOGITS
    th
    0.81
     percent
    0.77
    %-
    0.74
    %"
    0.74
    %
    0.73
     consecutive
    0.71
    %,
    0.69
    deg
    0.69
    °
    0.68
     stitches
    0.68
    Activations Density 0.412%

    No Known Activations