Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 2611
    Prev
    Next
    INDEX
    Explanations

    terms related to political entities, particularly countries and political parties

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Arab states and related geopolitical terms

    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
     advis
    -0.84
    idious
    -0.72
     contaminated
    -0.70
    bilt
    -0.63
    worthy
    -0.63
    axter
    -0.62
    USS
    -0.62
    cius
    -0.61
    cot
    -0.60
     hysteria
    -0.60
    POSITIVE LOGITS
     Alliance
    0.90
     Appeal
    0.88
     Movement
    0.85
     Conference
    0.84
     Institution
    0.84
     Association
    0.84
     Regiment
    0.84
     Society
    0.83
     Emirates
    0.83
     Assembly
    0.82
    Activations Density 0.130%

    No Known Activations