© 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 EvalsExportsAPI 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. 0-RES-JB
    11. 9777
    Prev
    Next
    INDEX
    Explanations

    the word "Society" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to societal concepts and terms related to communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     photoc
    -0.76
     Oath
    -0.73
     closures
    -0.72
     Cruise
    -0.68
     rede
    -0.68
    schild
    -0.66
     Macron
    -0.64
     Brexit
    -0.61
     cleaners
    -0.61
     Corbyn
    -0.60
    POSITIVE LOGITS
    soc
    2.60
    apolis
    2.55
    Soc
    2.46
    uno
    1.07
    Height
    0.99
    Orig
    0.92
     stout
    0.92
     Hemp
    0.86
    resso
    0.86
    esa
    0.84
    Activations Density 0.054%

    No Known Activations