© 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. 2-RES-JB
    11. 19641
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly focusing on Japanese names like "Kawashima"

    oai_token-act-pair · gpt-3.5-turbo

    references to prominent individuals or notable names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istically
    -0.74
    xual
    -0.74
    pmwiki
    -0.72
    llor
    -0.71
    owder
    -0.70
    udic
    -0.69
     Murdoch
    -0.69
     vain
    -0.68
     Flight
    -0.68
    ugu
    -0.67
    POSITIVE LOGITS
    asaki
    1.07
     Kaw
    1.05
    ©¶æ¥µ
    0.98
    enne
    0.95
    aii
    0.94
    eco
    0.86
    apon
    0.82
    ota
    0.81
    halla
    0.80
    KEN
    0.77
    Activations Density 0.010%

    No Known Activations