© 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. 4-RES-JB
    11. 1744
    Prev
    Next
    INDEX
    Explanations

    explanations or justifications within text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "explained" in various contexts

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

    No Comments

    Negative Logits
    ascus
    -0.81
    venge
    -0.75
    cess
    -0.74
    etooth
    -0.73
    illet
    -0.72
    estial
    -0.71
    jet
    -0.70
    naissance
    -0.70
    inal
    -0.69
    sembly
    -0.68
    POSITIVE LOGITS
     why
    1.02
     WHY
    0.93
     how
    0.81
     explaining
    0.77
     succinct
    0.76
    udic
    0.75
    ¿½
    0.74
     explains
    0.74
     explain
    0.74
     concise
    0.73
    Activations Density 0.029%

    No Known Activations