© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 23099
    Prev
    Next
    INDEX
    Explanations

    references to the website "Kotaku" and potentially similar terms

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the names "Kot" and "Kap"

    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
    xual
    -0.80
    IBLE
    -0.77
     tremend
    -0.76
    phrine
    -0.73
    iments
    -0.71
    uration
    -0.69
    omething
    -0.67
     mosqu
    -0.67
    afort
    -0.67
    mingham
    -0.66
    POSITIVE LOGITS
    lar
    0.95
    aepernick
    0.83
    kat
    0.81
     Rowling
    0.79
    zig
    0.78
     Osw
    0.77
    zeb
    0.72
    pps
    0.72
    emp
    0.71
     Noon
    0.68
    Activations Density 0.037%

    No Known Activations