© 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. 1749
    Prev
    Next
    INDEX
    Explanations

    questions in the text

    oai_token-act-pair · gpt-3.5-turbo

    questions that prompt engagement or encourage action

    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
    aling
    -0.67
    ality
    -0.66
     foreground
    -0.66
    jam
    -0.66
    forth
    -0.63
    ema
    -0.63
    iculture
    -0.62
    athe
    -0.62
    riel
    -0.60
    urnal
    -0.60
    POSITIVE LOGITS
     Check
    1.06
     Try
    1.00
     Become
    0.98
     Consider
    0.94
     Nope
    0.94
     Cancel
    0.94
     Subscribe
    0.92
     Congratulations
    0.90
     Find
    0.90
     Want
    0.89
    Activations Density 0.071%

    No Known Activations