© 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. 10-RES-JB
    11. 18655
    Prev
    Next
    INDEX
    Explanations

    names related to Middle Eastern individuals or groups, particularly those associated with conflicts or politics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to military groups and individuals involved in conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wilde
    -0.84
     Chloe
    -0.82
     Titanic
    -0.80
     Robo
    -0.76
     Poles
    -0.75
     Poland
    -0.73
     Wilhelm
    -0.73
     Nadu
    -0.73
     Polish
    -0.70
     Columbus
    -0.69
    POSITIVE LOGITS
    awi
    1.35
    zbollah
    1.28
    qqa
    1.27
    abi
    1.23
    aq
    1.16
    adi
    1.12
    azeera
    1.09
    ayn
    1.07
    Iraq
    1.05
    raq
    1.05
    Activations Density 0.140%

    No Known Activations