© 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. 10-RES-JB
    11. 10244
    Prev
    Next
    INDEX
    Explanations

    questions beginning with "Why" followed by a statement or action

    oai_token-act-pair · gpt-3.5-turbo

    questions or inquiries beginning with "why."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interstitial
    -0.75
    Laughs
    -0.64
    iece
    -0.61
    apsed
    -0.60
    marked
    -0.60
    eki
    -0.60
    tnc
    -0.59
    agonists
    -0.59
    spir
    -0.57
    engers
    -0.57
    POSITIVE LOGITS
     bother
    1.20
     do
    0.96
     did
    0.96
     aren
    0.91
     does
    0.90
     shouldn
    0.87
     wouldn
    0.83
    brow
    0.82
     weren
    0.81
     should
    0.80
    Activations Density 0.034%

    No Known Activations