© 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. 2-RES-JB
    11. 23053
    Prev
    Next
    INDEX
    Explanations

    instances of the word "think"

    oai_token-act-pair · gpt-3.5-turbo

    indicative phrases about the act of thinking

    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
    conservancy
    -0.74
    clad
    -0.73
     Adin
    -0.71
    Naz
    -0.70
    ague
    -0.68
     clad
    -0.66
    recorded
    -0.66
    ORPG
    -0.65
    announced
    -0.64
    east
    -0.62
    POSITIVE LOGITS
    pad
    0.70
     provoking
    0.68
    IUM
    0.67
     thinkers
    0.67
     minds
    0.66
     Thought
    0.66
    bia
    0.65
    furt
    0.65
    ij士
    0.65
    agram
    0.65
    Activations Density 0.055%

    No Known Activations