© 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. 20418
    Prev
    Next
    INDEX
    Explanations

    phrases related to arguments, conclusions, and reasoning

    oai_token-act-pair · gpt-3.5-turbo

    statements expressing conclusions, assumptions, or claims

    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
    abouts
    -0.68
    worth
    -0.64
    gie
    -0.62
    Exit
    -0.62
    inventoryQuantity
    -0.59
    apeake
    -0.59
    ciating
    -0.58
    elight
    -0.57
     Pastebin
    -0.56
    nect
    -0.55
    POSITIVE LOGITS
     that
    1.25
     moreover
    1.09
    that
    1.07
     furthermore
    1.06
     therefore
    0.95
     however
    0.85
     convinc
    0.83
     emphatically
    0.79
     THAT
    0.79
     unequivocally
    0.76
    Activations Density 0.435%

    No Known Activations