Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 17928
    Prev
    Next
    INDEX
    Explanations

    phrases indicating exceptions or exclusions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "except."

    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
    mary
    -0.68
    yrs
    -0.66
    venture
    -0.65
    pt
    -0.63
    hetamine
    -0.62
    foreseen
    -0.61
    election
    -0.61
    gged
    -0.60
    ãĤ¿
    -0.60
    rounder
    -0.60
    POSITIVE LOGITS
    ional
    1.14
     insofar
    0.81
    ords
    0.74
     Zucker
    0.73
    arus
    0.72
    icut
    0.65
    livious
    0.65
    ions
    0.65
    inarily
    0.63
    MENTS
    0.63
    Activations Density 0.021%

    No Known Activations