© 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. 5170
    Prev
    Next
    INDEX
    Explanations

    questions starting with "How do we..." or "How do you..." referring to various actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    repeated questions and inquiries within the text

    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
    scl
    -0.61
     Coffin
    -0.60
    hao
    -0.58
     Skies
    -0.58
    letter
    -0.57
     Seek
    -0.55
     Kau
    -0.55
    requisite
    -0.55
    Cra
    -0.55
    slave
    -0.54
    POSITIVE LOGITS
     reconcile
    1.10
     reconcil
    1.04
     cope
    0.99
    Ô
    0.91
     coping
    0.90
     fared
    0.89
     fare
    0.86
     managed
    0.82
     manage
    0.80
     navigate
    0.78
    Activations Density 0.130%

    No Known Activations