© 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. 0-RES-JB
    11. 12726
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the person "Sergio Pérez."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     imperson
    -0.65
     blanket
    -0.64
     watch
    -0.64
     Sponge
    -0.64
     policies
    -0.63
     equal
    -0.62
     equals
    -0.62
     thrott
    -0.61
     CEOs
    -0.61
     coaches
    -0.60
    POSITIVE LOGITS
    rez
    5.47
    reon
    1.17
    rend
    1.16
    vez
    1.15
    reb
    1.09
    rar
    1.07
    irez
    1.06
    pez
    1.04
    rance
    1.04
    ritz
    1.03
    Activations Density 0.008%

    No Known Activations