© 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. 10-RES-JB
    11. 722
    Prev
    Next
    INDEX
    Explanations

    references to the name "Van"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Van" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.67
    ilial
    -0.64
    inals
    -0.64
    IJ
    -0.63
     reluct
    -0.61
    inally
    -0.61
     retina
    -0.61
    omething
    -0.60
    ãģĨ
    -0.60
    */(
    -0.60
    POSITIVE LOGITS
    quished
    1.25
     Gaal
    1.16
    ishing
    1.11
    adium
    1.10
    ishes
    1.04
    essa
    1.03
     Hels
    0.99
    illa
    0.95
    ished
    0.91
    illas
    0.89
    Activations Density 0.017%

    No Known Activations