© 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. 9-RES-JB
    11. 18546
    Prev
    Next
    INDEX
    Explanations

    phrases expressing strong insistence or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "insist" in various forms, indicating strong assertions or demands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.74
    gone
    -0.71
    spl
    -0.70
    ãĥĥãĥĪ
    -0.69
    DragonMagazine
    -0.65
    EStreamFrame
    -0.64
    sten
    -0.64
    posure
    -0.63
    gallery
    -0.62
    ãĤ¡
    -0.62
    POSITIVE LOGITS
    ently
    1.16
     vehemently
    0.87
     upon
    0.84
    ially
    0.83
    atively
    0.82
    uously
    0.79
     otherwise
    0.76
    antly
    0.75
     abstinence
    0.74
     adherence
    0.73
    Activations Density 0.031%

    No Known Activations