© 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. 13883
    Prev
    Next
    INDEX
    Explanations

    mentions of historical figures and companies, particularly related to inventions and bankruptcies

    oai_token-act-pair · gpt-3.5-turbo

    references to historical figures and their inventions or contributions

    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
    zbollah
    -0.88
    ISIS
    -0.86
    ebin
    -0.83
    iberal
    -0.82
     Benghazi
    -0.81
     YPG
    -0.80
    uterte
    -0.80
     Daesh
    -0.79
    bnb
    -0.76
     ISIS
    -0.76
    POSITIVE LOGITS
     Edison
    1.49
     1909
    1.37
     1927
    1.30
     1935
    1.29
     1896
    1.29
     1910
    1.29
     1931
    1.28
     1934
    1.27
     1904
    1.26
     1908
    1.26
    Activations Density 0.677%

    No Known Activations