© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6402
    Prev
    Next
    INDEX
    Explanations

    questions starting with "How"

    oai_token-act-pair · gpt-3.5-turbo

    questions that start with "How"

    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
     laps
    -0.66
    ank
    -0.64
    erate
    -0.62
     recess
    -0.62
     prevail
    -0.61
    pect
    -0.58
     prelim
    -0.58
     terminated
    -0.58
    ãĥ¼ãĥ³
    -0.57
    stone
    -0.57
    POSITIVE LOGITS
     How
    2.95
    How
    2.17
     HOW
    2.02
     Why
    1.95
    how
    1.78
     What
    1.72
     how
    1.57
    HOW
    1.49
     Who
    1.42
     Where
    1.42
    Activations Density 0.013%

    No Known Activations