© 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. 11-RES-JB
    11. 13689
    Prev
    Next
    INDEX
    Explanations

    names of historical figures

    oai_token-act-pair · gpt-3.5-turbo

    references to specific cultural or historical groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    FIN
    -0.68
     Clicker
    -0.64
     WITHOUT
    -0.63
     MPG
    -0.63
     RT
    -0.63
    ļéĨĴ
    -0.62
    ++)
    -0.62
    impact
    -0.60
     JPM
    -0.60
    STON
    -0.60
    POSITIVE LOGITS
     tribe
    1.36
     clan
    1.34
     Tribe
    1.24
    ians
    1.18
     Clan
    1.17
     clans
    1.16
     sisters
    1.13
     dynasty
    1.11
     Rebellion
    1.08
     tribes
    1.07
    Activations Density 0.287%

    No Known Activations