© 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. 19352
    Prev
    Next
    INDEX
    Explanations

    personal names starting with "S" or "T"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter combinations consisting of the vowels 'u' and 'i'

    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
    enegger
    -0.88
    ruary
    -0.80
    lished
    -0.72
    ancial
    -0.71
    selves
    -0.69
    ð
    -0.69
    hesda
    -0.69
    nesday
    -0.67
    taboola
    -0.67
     Forbidden
    -0.65
    POSITIVE LOGITS
     Patel
    0.97
    opal
    0.95
    oti
    0.83
     Koh
    0.82
     Kov
    0.81
    ansky
    0.81
    eta
    0.80
    atis
    0.80
    idis
    0.80
     Khan
    0.79
    Activations Density 0.130%

    No Known Activations