© 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. 8502
    Prev
    Next
    INDEX
    Explanations

    words related to sweet baked goods like muffins

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "uff" which may indicate a specific emphasis or emotional tone

    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
    CHR
    -0.74
     lapse
    -0.66
    metic
    -0.65
    chrome
    -0.64
    xual
    -0.63
    obal
    -0.62
    matically
    -0.62
    Hunt
    -0.61
     erg
    -0.60
     horizontally
    -0.59
    POSITIVE LOGITS
    ington
    1.11
    ield
    1.06
    IELD
    1.01
    iculty
    0.94
    alo
    0.94
    uff
    0.90
    ucket
    0.85
    ieri
    0.82
    ier
    0.81
    puff
    0.80
    Activations Density 0.027%

    No Known Activations