© 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. 7-RES-JB
    11. 2726
    Prev
    Next
    INDEX
    Explanations

    adverbs related to a high degree or extent

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that indicate a significant degree or extent

    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
     GHC
    -0.64
     scramble
    -0.61
     Might
    -0.60
    heses
    -0.58
     Carbuncle
    -0.58
     Tackle
    -0.57
     Punch
    -0.57
    olulu
    -0.56
     Surgery
    -0.54
     eruption
    -0.54
    POSITIVE LOGITS
    into
    0.86
     toward
    0.81
     onward
    0.77
    eper
    0.77
     into
    0.75
     onto
    0.73
    azard
    0.73
    thin
    0.70
    oward
    0.70
    onto
    0.69
    Activations Density 0.179%

    No Known Activations