© 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. 6-RES-JB
    11. 12058
    Prev
    Next
    INDEX
    Explanations

    French words and names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character "é" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utterstock
    -0.78
    etsk
    -0.77
    pread
    -0.77
    ageddon
    -0.75
    INESS
    -0.70
    enged
    -0.70
     Cobra
    -0.67
     redistributed
    -0.66
    berra
    -0.64
    multipl
    -0.64
    POSITIVE LOGITS
    lé
    1.18
     Dame
    0.89
     é
    0.88
    vez
    0.87
    ré
    0.86
    rez
    0.83
    ité
    0.82
    ration
    0.82
    mie
    0.80
    cé
    0.79
    Activations Density 0.022%

    No Known Activations