© 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. 9-RES-JB
    11. 15974
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names such as "Susan."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Susan"

    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
    ORD
    -0.80
    iculty
    -0.78
    cffffcc
    -0.72
    unct
    -0.70
    riter
    -0.65
    olkien
    -0.64
    erent
    -0.64
    psey
    -0.64
     warped
    -0.64
    ebus
    -0.62
    POSITIVE LOGITS
    ne
    0.97
    icide
    0.97
    gha
    0.96
    jit
    0.86
    anne
    0.86
    ja
    0.85
    icides
    0.80
    atan
    0.79
    otte
    0.79
    mination
    0.78
    Activations Density 0.033%

    No Known Activations