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

    Neuronpedia

    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. 7-RES-JB
    11. 2137
    Prev
    Next
    INDEX
    Explanations

    phrases indicating raising questions or doubts about certain topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to raising questions or possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vanquished
    -0.65
     Melbourne
    -0.59
    arded
    -0.57
     conquered
    -0.57
    ©¶æ
    -0.57
    winter
    -0.56
     Babylon
    -0.55
     Oak
    -0.55
    oped
    -0.55
    ãĥ¼ãĤ¯
    -0.55
    POSITIVE LOGITS
     suspicions
    0.76
     cred
    0.74
     possibilities
    0.73
    msg
    0.73
     Logged
    0.70
     possibility
    0.69
     insight
    0.69
     credibility
    0.67
     GOODMAN
    0.66
    sense
    0.66
    Activations Density 0.583%

    No Known Activations