© 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. 23020
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "except"

    oai_token-act-pair · gpt-3.5-turbo

    the word "except" and its variations, indicating exclusions or contrasts

    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
    ãĤ¿
    -0.65
    aimon
    -0.62
     Flavoring
    -0.61
    cent
    -0.60
    hetamine
    -0.59
    idered
    -0.58
    Äĩ
    -0.58
    pt
    -0.57
    itiz
    -0.57
     contag
    -0.56
    POSITIVE LOGITS
    ional
    1.26
    arus
    0.79
    ords
    0.76
    ¯
    0.76
     insofar
    0.72
    icut
    0.71
    livious
    0.67
    ions
    0.67
    ing
    0.67
    ments
    0.66
    Activations Density 0.027%

    No Known Activations