© 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. 9-RES-JB
    11. 13460
    Prev
    Next
    INDEX
    Explanations

    instances where someone is asking for or providing explanations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "explain" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    luster
    -0.81
    itton
    -0.71
    oreal
    -0.69
    sembly
    -0.69
    Ranked
    -0.67
    oso
    -0.64
    inating
    -0.63
    rica
    -0.63
    estial
    -0.63
    ille
    -0.61
    POSITIVE LOGITS
     why
    1.55
     WHY
    1.31
    why
    1.16
     how
    1.15
    how
    0.89
     Why
    0.82
     HOW
    0.80
     concise
    0.78
     what
    0.76
     succinct
    0.73
    Activations Density 0.057%

    No Known Activations