© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 23539
    Prev
    Next
    INDEX
    Explanations

    commonly used words related to the action of proceeding or continuing with a task

    oai_token-act-pair · gpt-3.5-turbo

    the use of the word "proceed" and its variants in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tek
    -0.87
    lder
    -0.74
    tal
    -0.73
    aez
    -0.71
    cup
    -0.71
    ton
    -0.71
    tu
    -0.70
    marked
    -0.69
    bie
    -0.68
    ty
    -0.67
    POSITIVE LOGITS
     onward
    0.94
     cautiously
    0.92
     Proceed
    0.87
     onwards
    0.79
     blindly
    0.78
    ively
    0.77
     calmly
    0.75
     smoothly
    0.75
    ansion
    0.74
     through
    0.73
    Activations Density 0.047%

    No Known Activations