© 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. 1919
    Prev
    Next
    INDEX
    Explanations

    names, likely related to a specific individual or company named Kos, Kro, Koz, Kre, and Kris

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or names

    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
    IBLE
    -0.85
    ENCE
    -0.69
    Ö¼
    -0.69
    drops
    -0.69
    cipl
    -0.68
    uous
    -0.68
    antly
    -0.68
    ible
    -0.67
    earable
    -0.65
    iments
    -0.65
    POSITIVE LOGITS
    laus
    0.91
     Klux
    0.91
    won
    0.90
    istani
    0.84
    lein
    0.82
    £ı
    0.82
    patrick
    0.82
    kat
    0.80
    lov
    0.78
    lyak
    0.76
    Activations Density 0.093%

    No Known Activations