© 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. 2-RES-JB
    11. 545
    Prev
    Next
    INDEX
    Explanations

    words containing the word root "vious" or "viously"

    oai_token-act-pair · gpt-4-turbo

    proper nouns and related words, possibly associated with characters or entities

    oai_token-act-pair · gpt-3.5-turbo

    words related to obviousness or things that are known

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olicited
    -0.65
    odium
    -0.65
    OH
    -0.64
    ische
    -0.64
    gravity
    -0.63
    ella
    -0.62
    rition
    -0.62
     tighter
    -0.62
    ocal
    -0.61
     peanuts
    -0.61
    POSITIVE LOGITS
    vious
    1.11
    vous
    0.99
    nesses
    0.91
     Previous
    0.89
     compr
    0.84
     Generations
    0.79
    irin
    0.77
     incarn
    0.76
     contrad
    0.76
    dayName
    0.73
    Activations Density 0.003%

    No Known Activations