© 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. 7-RES-JB
    11. 9985
    Prev
    Next
    INDEX
    Explanations

    statements where someone is being asked to provide an explanation or clarify a concept

    oai_token-act-pair · gpt-3.5-turbo

    instances 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 @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    luster
    -0.74
    illet
    -0.72
    Ranked
    -0.71
    ches
    -0.70
    estial
    -0.68
    sembly
    -0.67
    ammy
    -0.66
    etooth
    -0.66
    berus
    -0.64
    bour
    -0.64
    POSITIVE LOGITS
     why
    1.22
     WHY
    1.10
    why
    0.97
     how
    0.90
    cases
    0.76
    ļéĨĴ
    0.76
     concise
    0.76
     succinct
    0.73
    how
    0.71
    ĸļ
    0.70
    Activations Density 0.057%

    No Known Activations