© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11-RES-JB
    11. 20673
    Prev
    Next
    INDEX
    Explanations

    references to military operations and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to various military or political groups, particularly in the context of conflict

    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
     Keynes
    -0.73
     Pru
    -0.70
     Schr
    -0.70
     Grimm
    -0.69
     Sci
    -0.69
     Cthulhu
    -0.68
     Inher
    -0.68
     Einstein
    -0.67
     Columbia
    -0.65
     Lovecraft
    -0.65
    POSITIVE LOGITS
    akh
    1.16
    usra
    1.14
    abi
    1.09
    adi
    1.03
    agh
    1.02
    aba
    1.00
    ihad
    0.99
    ema
    0.99
    Syrian
    0.99
    ouri
    0.97
    Activations Density 0.147%

    No Known Activations