© 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. 4-RES-JB
    11. 7535
    Prev
    Next
    INDEX
    Explanations

    the word "proceed" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "proceed" and its variants

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

    No Comments

    Negative Logits
    tal
    -0.78
    ton
    -0.72
    ched
    -0.71
    aptic
    -0.71
    cher
    -0.69
    etimes
    -0.69
    ching
    -0.69
    eye
    -0.67
    chest
    -0.67
    lder
    -0.66
    POSITIVE LOGITS
     Proceed
    0.90
     "$:/
    0.80
     proceed
    0.78
     proceeds
    0.77
    SourceFile
    0.76
    icter
    0.76
    ivism
    0.73
    cffffcc
    0.73
    itters
    0.70
     withd
    0.67
    Activations Density 0.017%

    No Known Activations