© 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. 17692
    Prev
    Next
    INDEX
    Explanations

    statistical information or study results

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating polling or survey results and suggestions

    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
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.75
    ufact
    -0.68
    thia
    -0.65
     redes
    -0.63
    via
    -0.63
     surrendered
    -0.63
    bart
    -0.63
    è»
    -0.63
     sidx
    -0.61
    gur
    -0.61
    POSITIVE LOGITS
     Orb
    0.67
     several
    0.60
     numerous
    0.60
     anomalies
    0.58
     discrepancies
    0.58
     Rasmussen
    0.57
     gaps
    0.57
     conclusive
    0.56
    rocket
    0.56
     dozens
    0.56
    Activations Density 0.188%

    No Known Activations