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. 4-RES-JB
    6. 17392
    Prev
    Next
    INDEX
    Explanations

    words related to the act of thinking

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "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
     Wrestling
    -0.71
    çĦ
    -0.70
    Ann
    -0.67
    henko
    -0.64
    clad
    -0.63
    any
    -0.63
     Adin
    -0.63
    Jer
    -0.62
    owship
    -0.62
    Merit
    -0.61
    POSITIVE LOGITS
    sonian
    0.78
     thinking
    0.76
    afia
    0.76
    ronics
    0.75
     provoking
    0.74
    zsche
    0.73
    ortment
    0.73
    cient
    0.72
     aloud
    0.71
     about
    0.71
    Activations Density 0.028%

    No Known Activations