© 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. 7235
    Prev
    Next
    INDEX
    Explanations

    phrases related to overwhelming or intense situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "del" or its variations

    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
    soever
    -0.69
    ratulations
    -0.67
    LESS
    -0.65
     Fields
    -0.61
    perse
    -0.60
    laus
    -0.59
    lessly
    -0.59
    LER
    -0.58
     Moonlight
    -0.57
    dal
    -0.57
    POSITIVE LOGITS
    uxe
    1.33
    uded
    1.02
    ights
    1.01
    ivery
    0.97
    ving
    0.96
     Toro
    0.93
    usive
    0.92
    uge
    0.91
    inqu
    0.85
    ined
    0.83
    Activations Density 0.017%

    No Known Activations