© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 9612
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific organization or brand, in this case, "Think" or "Think Progress."

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of the word "Think."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unresolved
    -0.73
    adal
    -0.71
     validity
    -0.70
     unsett
    -0.70
    ĩ
    -0.70
     immun
    -0.69
     final
    -0.67
     bol
    -0.65
     eligibility
    -0.65
     adjustment
    -0.64
    POSITIVE LOGITS
     Think
    3.65
    Think
    3.00
    think
    2.29
     Thought
    1.74
     Thinking
    1.62
     Imagine
    1.60
    thought
    1.38
     think
    1.36
     Idea
    1.36
    Imagine
    1.35
    Activations Density 0.017%

    No Known Activations