© 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. 2-RES-JB
    11. 21873
    Prev
    Next
    INDEX
    Explanations

    interrogative sentences starting with the word "Which"

    oai_token-act-pair · gpt-3.5-turbo

    the word "Which" in various contexts, possibly indicating questions or choices

    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
    athi
    -0.72
    pad
    -0.68
    burg
    -0.64
    Gy
    -0.63
    GY
    -0.63
    steen
    -0.62
    ding
    -0.61
     Antar
    -0.61
    borg
    -0.61
    gy
    -0.61
    POSITIVE LOGITS
    soever
    1.07
    ãĥ¯ãĥ³
    0.81
     brings
    0.77
    xual
    0.75
    ispers
    0.73
    chwitz
    0.71
    espie
    0.70
    akespeare
    0.70
     begs
    0.69
     contrasts
    0.69
    Activations Density 0.071%

    No Known Activations