© 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. 4-RES-JB
    11. 1837
    Prev
    Next
    INDEX
    Explanations

    the word "think."

    oai_token-act-pair · gpt-3.5-turbo

    expressions and discussions related to the concept of thinking

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

    No Comments

    Negative Logits
    ague
    -0.69
    clad
    -0.68
    conservancy
    -0.65
     Adin
    -0.63
    catentry
    -0.62
    yna
    -0.62
    anca
    -0.60
    Merit
    -0.60
    çĦ
    -0.60
    Jer
    -0.60
    POSITIVE LOGITS
    orial
    0.77
    pad
    0.74
     aloud
    0.71
     Turing
    0.67
    onymous
    0.66
     provoking
    0.66
    ileaks
    0.66
    onom
    0.65
    IUM
    0.64
    rodu
    0.64
    Activations Density 0.066%

    No Known Activations