Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 10291
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences containing the word "Obviously" followed by a statement

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate certainty or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sway
    -0.71
     mouth
    -0.65
     sights
    -0.65
     yoga
    -0.65
     secret
    -0.64
     backdrop
    -0.61
     rag
    -0.61
    olog
    -0.61
     kindred
    -0.61
     shadow
    -0.61
    POSITIVE LOGITS
    Effective
    0.80
    resy
    0.78
     Helpful
    0.77
    chwitz
    0.77
    Berry
    0.76
    wcsstore
    0.74
    Obviously
    0.72
     Correct
    0.71
    Different
    0.70
    Pixel
    0.70
    Activations Density 0.010%

    No Known Activations