© 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. 17238
    Prev
    Next
    INDEX
    Explanations

    names or terms related to the surname "Van" or "Von"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals or names in the text

    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
     NETWORK
    -0.84
     reluct
    -0.80
    mable
    -0.70
    IJ
    -0.69
     casc
    -0.69
     cryst
    -0.69
    ĨĴ
    -0.68
    ģĸ
    -0.68
    ij士
    -0.66
    NES
    -0.65
    POSITIVE LOGITS
    igans
    0.99
    ishing
    0.97
    hoe
    0.92
    loo
    0.91
    van
    0.91
    anth
    0.90
    quez
    0.86
    ovich
    0.86
    illa
    0.85
    ning
    0.83
    Activations Density 0.010%

    No Known Activations