© 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. 11308
    Prev
    Next
    INDEX
    Explanations

    phrases related to the action of treating something in a specific manner

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to treatment and perception of concepts or individuals

    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
    untled
    -0.81
    erity
    -0.80
    abee
    -0.72
    rower
    -0.69
    raged
    -0.67
    haired
    -0.66
    ãĤ¼ãĤ¦ãĤ¹
    -0.66
    ffe
    -0.65
    CHA
    -0.64
    isphere
    -0.64
    POSITIVE LOGITS
    ¥µ
    0.84
     sacred
    0.82
     precedent
    0.82
     gospel
    0.79
     homework
    0.78
     canon
    0.77
     belonging
    0.74
     objectively
    0.73
     worthwhile
    0.73
     scripture
    0.72
    Activations Density 0.263%

    No Known Activations