© 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. 8-RES-JB
    11. 1053
    Prev
    Next
    INDEX
    Explanations

    names of universities and brands, particularly "Hofstra," "Guinness," "Porsche," and "Ferrari."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of brands and notable entities associated with luxury and recognition, particularly in the context of records and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atin
    -0.86
    uci
    -0.85
    isions
    -0.84
    hips
    -0.83
     externalToEVAOnly
    -0.83
    espie
    -0.81
    ibrary
    -0.81
    obyl
    -0.81
    inson
    -0.81
    ided
    -0.80
    POSITIVE LOGITS
    llor
    0.81
     Centauri
    0.65
    ellectual
    0.62
     Bran
    0.62
     grease
    0.61
     paternity
    0.61
    rers
    0.60
     Grande
    0.60
    PDATE
    0.59
    fort
    0.59
    Activations Density 0.115%

    No Known Activations