© 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 EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 12634
    Prev
    Next
    INDEX
    Explanations

    terms related to specific cultural practices or concepts, specifically involving Japanese language and customs

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cultural practices or traditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CLASSIFIED
    -0.86
     Tinker
    -0.76
     Mutant
    -0.74
     JPM
    -0.74
     Preferences
    -0.73
     MILL
    -0.73
     Opportun
    -0.72
    Bright
    -0.72
    PsyNetMessage
    -0.71
     Canaveral
    -0.71
    POSITIVE LOGITS
    á¹
    1.17
    ensis
    1.11
    Äĵ
    1.03
    á¸
    1.02
    Ä«
    0.98
    Äģ
    0.95
    Åį
    0.95
    É
    0.93
    qa
    0.89
    acha
    0.89
    Activations Density 0.230%

    No Known Activations