© 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. 4-RES-JB
    11. 17161
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "agon" at varying activation levels

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "agon" related to struggles or conflicts

    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
    bered
    -0.73
    ©¶æ
    -0.73
    natureconservancy
    -0.64
    putable
    -0.63
     plurality
    -0.63
    avid
    -0.63
    said
    -0.62
    ples
    -0.62
    animate
    -0.62
     Lori
    -0.61
    POSITIVE LOGITS
    naire
    1.33
    xon
    0.97
    naires
    0.92
    andise
    0.86
    ous
    0.86
    insula
    0.84
    osity
    0.82
    agon
    0.82
    otine
    0.82
    ocity
    0.82
    Activations Density 0.009%

    No Known Activations