© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 2309
    Prev
    Next
    INDEX
    Explanations

    Turkish pronunciations

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    elements related to transcription or phonetic notation

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     bankruptcy
    -0.61
     relegation
    -0.60
     unbelievable
    -0.60
     emergencies
    -0.58
     consolation
    -0.58
     Chavez
    -0.57
     unprecedented
    -0.57
     unforeseen
    -0.57
     Disneyland
    -0.57
     approvals
    -0.56
    POSITIVE LOGITS
    É
    1.97
    ËĪ
    1.86
    Ê
    1.69
    Äĵ
    1.54
    Ä«
    1.52
    Ë
    1.50
    Å«
    1.46
    Åį
    1.45
    Ì
    1.44
    Äģ
    1.44
    Activations Density 0.064%

    No Known Activations