© 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. 6-RES-JB
    11. 14547
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases related to medical conditions or procedures

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and symbols that might indicate questions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilee
    -0.70
     Gur
    -0.67
     treasury
    -0.66
    itiz
    -0.64
    jong
    -0.63
     contrace
    -0.63
    ified
    -0.61
    ework
    -0.61
     hasht
    -0.59
     predec
    -0.59
    POSITIVE LOGITS
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.76
     Unloaded
    0.75
    RESULTS
    0.73
    è¦ļéĨĴ
    0.72
    20439
    0.72
     Characters
    0.72
    âķ
    0.71
    EStream
    0.69
    SELECT
    0.69
    ï¸
    0.69
    Activations Density 0.073%

    No Known Activations