© 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. 1318
    Prev
    Next
    INDEX
    Explanations

    Pokémon-related terms and card game actions

    oai_token-act-pair · gpt-3.5-turbo

    special characters or unique symbols, possibly related to coded or alternate text formats

    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
    arton
    -0.94
    estern
    -0.89
    ebus
    -0.86
    olf
    -0.82
    zees
    -0.81
    olicy
    -0.79
    olit
    -0.76
     reinvest
    -0.75
    achy
    -0.74
    iets
    -0.73
    POSITIVE LOGITS
    ãĥ¼ãĥ
    1.72
    ãĥ¼ãĥ³
    1.69
    ãĥ©
    1.63
    ãĥ³
    1.60
    ãĤ¿
    1.57
    ãĤ¯
    1.55
    ãĥ«
    1.55
    ãĤ«
    1.54
    ãĥª
    1.53
    ãĤ³
    1.52
    Activations Density 0.016%

    No Known Activations