© 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. 11-RES-JB
    11. 2622
    Prev
    Next
    INDEX
    Explanations

    phrases related to arguing a point or making a case

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate conclusions or arguments presented in a discussion or analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emort
    -0.83
    tesy
    -0.67
    ascus
    -0.65
    phabet
    -0.63
    abouts
    -0.62
    soType
    -0.61
    aband
    -0.61
     Pastebin
    -0.60
    lease
    -0.60
    ĪĴ
    -0.60
    POSITIVE LOGITS
     that
    1.26
    that
    1.01
     persu
    0.87
     THAT
    0.82
     causation
    0.79
     convinc
    0.78
     unequivocally
    0.76
    That
    0.70
     emphatically
    0.69
     otherwise
    0.69
    Activations Density 0.319%

    No Known Activations