© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 11696
    Prev
    Next
    INDEX
    Explanations

    phrases introducing additional information or comments

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "by the way."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    prus
    -0.73
    natureconservancy
    -0.71
    ilater
    -0.70
    "},"
    -0.66
    izens
    -0.64
    ĸļ
    -0.63
    untarily
    -0.60
    urred
    -0.60
    ËĪ
    -0.59
    viol
    -0.59
    POSITIVE LOGITS
     congr
    0.83
    ,
    0.81
     congratulations
    0.76
     suppose
    0.75
    adays
    0.75
     remember
    0.74
    ,.
    0.70
    âĢ¦)
    0.70
    quote
    0.67
    :
    0.66
    Activations Density 0.075%

    No Known Activations