© 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. 10081
    Prev
    Next
    INDEX
    Explanations

    questions or prompts starting with the word "What"

    oai_token-act-pair · gpt-3.5-turbo

    questions beginning with the word "What."

    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
    apsed
    -0.74
    swick
    -0.66
    emp
    -0.64
    hew
    -0.64
    pic
    -0.63
    iva
    -0.61
    Lago
    -0.61
    ammed
    -0.61
    rolley
    -0.59
    abel
    -0.59
    POSITIVE LOGITS
     do
    0.94
     does
    0.94
     kinds
    0.91
     distinguishes
    0.89
     determines
    0.88
     happens
    0.87
     motiv
    0.84
     qualifies
    0.82
     are
    0.81
     did
    0.81
    Activations Density 0.054%

    No Known Activations