© 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. 7-RES-JB
    11. 21215
    Prev
    Next
    INDEX
    Explanations

    sentences that start with "You know," or similar phrases

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases that initiate with "You know."

    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
    士
    -0.80
    omal
    -0.76
    aq
    -0.75
    entials
    -0.74
    erity
    -0.73
    pak
    -0.71
    rehend
    -0.70
    ãĤº
    -0.70
    uscript
    -0.69
    HL
    -0.67
    POSITIVE LOGITS
     uh
    0.80
     maybe
    0.79
     kinda
    0.72
     anecd
    0.71
    depending
    0.70
     sensing
    0.69
     sort
    0.65
     whatever
    0.65
    soType
    0.64
     yeah
    0.64
    Activations Density 0.051%

    No Known Activations