© 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. 7-RES-JB
    11. 23987
    Prev
    Next
    INDEX
    Explanations

    names of specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imately
    -0.83
    ashtra
    -0.74
    vous
    -0.65
    ï¸ı
    -0.64
    yip
    -0.63
     broom
    -0.63
    BLIC
    -0.62
    minecraft
    -0.61
     Haram
    -0.59
     LEDs
    -0.59
    POSITIVE LOGITS
    asley
    0.67
    Marsh
    0.64
    ukes
    0.64
    canon
    0.63
     Kelley
    0.63
    vine
    0.60
    mberg
    0.59
     Cullen
    0.57
    oyer
    0.57
     Johnston
    0.57
    Activations Density 0.088%

    No Known Activations