© 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. 1024
    Prev
    Next
    INDEX
    Explanations

    words related to various subjects such as art, politics, human behavior, and social issues

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to card games and strategy

    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
    farious
    -0.49
    ploma
    -0.47
    bernatorial
    -0.46
    sylv
    -0.46
    abus
    -0.45
    chuk
    -0.45
    rium
    -0.44
    udic
    -0.43
     Pixie
    -0.42
    eligible
    -0.41
    POSITIVE LOGITS
    pmwiki
    0.52
    bably
    0.50
     è£ıè
    0.45
     android
    0.44
     largeDownload
    0.43
    NetMessage
    0.42
    disk
    0.41
     auto
    0.40
    )!
    0.40
    !--
    0.40
    Activations Density 2.808%

    No Known Activations