© 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. 0-RES-JB
    11. 19068
    Prev
    Next
    INDEX
    Explanations

    question words

    oai_token-act-pair · gpt-3.5-turbo

    the presence of "WH" questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alto
    -0.67
    anon
    -0.65
     Bok
    -0.64
     Vent
    -0.62
    onte
    -0.62
     Milan
    -0.62
    enery
    -0.62
    arte
    -0.61
    ãĥ¼ãĥĨãĤ£
    -0.61
     Lib
    -0.61
    POSITIVE LOGITS
    WH
    3.16
     WH
    3.14
    WHO
    2.13
     WHO
    1.98
    WHAT
    1.41
     WHERE
    1.40
     WHAT
    1.38
     HOW
    1.38
    HOW
    1.32
     WOR
    1.32
    Activations Density 0.027%

    No Known Activations