© 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. 2-RES-JB
    11. 23761
    Prev
    Next
    INDEX
    Explanations

    instances of the word "asking."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "asking" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adj
    -0.68
    zinski
    -0.68
    stream
    -0.68
    ACP
    -0.67
    cutting
    -0.67
    lim
    -0.65
    Lago
    -0.63
    smoking
    -0.62
    photos
    -0.61
    cyclop
    -0.60
    POSITIVE LOGITS
     rhet
    1.00
    naires
    0.97
     probing
    0.90
     questions
    0.89
    FontSize
    0.87
     passers
    0.85
     asked
    0.83
    erville
    0.82
     asking
    0.76
     him
    0.73
    Activations Density 0.016%

    No Known Activations