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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 19357
    Prev
    Next
    INDEX
    Explanations

    instances of the word "think"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences 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
    ¶
    -0.75
    mate
    -0.72
    Completed
    -0.71
     Required
    -0.63
    inal
    -0.61
    posts
    -0.59
     provided
    -0.58
    Pg
    -0.58
    loader
    -0.57
    falls
    -0.57
    POSITIVE LOGITS
     think
    3.10
    think
    2.23
     Think
    1.84
    Think
    1.80
     thinks
    1.80
     reckon
    1.66
     imagine
    1.63
     believe
    1.61
     suppose
    1.53
     thinking
    1.51
    Activations Density 0.059%

    No Known Activations