© 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. 10-RES-JB
    11. 9932
    Prev
    Next
    INDEX
    Explanations

    arguments or attempts to persuade others in written texts

    oai_token-act-pair · gpt-3.5-turbo

    words related to debating or making arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gallery
    -0.68
    pta
    -0.65
     ILCS
    -0.63
    cffffcc
    -0.62
    ascript
    -0.62
    anie
    -0.61
    hook
    -0.60
     Pastebin
    -0.60
    lio
    -0.60
    beam
    -0.60
    POSITIVE LOGITS
     against
    1.28
     convinc
    1.16
     passionately
    1.15
     vehemently
    1.11
     forcefully
    1.08
     persu
    1.07
    against
    1.03
     stren
    0.93
     vigorously
    0.89
    Against
    0.88
    Activations Density 0.046%

    No Known Activations