© 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. 12-RES-JB
    11. 3828
    Prev
    Next
    INDEX
    Explanations

    personal opinions and preferences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to complex characters and their relationships in narratives

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Woodward
    -0.70
     concluding
    -0.66
     Windsor
    -0.62
     Gideon
    -0.59
     FISA
    -0.58
     premature
    -0.58
     preliminary
    -0.58
     twilight
    -0.57
     Liberty
    -0.57
     Kissinger
    -0.57
    POSITIVE LOGITS
    âĢ
    1.15
    ÃĥÃĤ
    0.99
    Ä
    0.89
    ¨
    0.86
    ÃĥÃĤÃĥÃĤ
    0.84
    ãĥĺãĥ©
    0.83
    âķIJ
    0.82
    âī
    0.79
     teasp
    0.79
    â
    0.79
    Activations Density 0.533%

    No Known Activations