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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9-RES-JB
    11. 16410
    Prev
    Next
    INDEX
    Explanations

    texts related to geopolitical conflicts, specifically regarding accusations and denials of involvement

    oai_token-act-pair · gpt-3.5-turbo

    mentions of geopolitical conflicts and accusations involving nations or government entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĵ
    -0.67
    mith
    -0.67
     Nope
    -0.64
     "âĢ¦
    -0.64
    âĢ¦]
    -0.63
     Alvin
    -0.63
    aukee
    -0.62
    "âĢ¦
    -0.62
     Operator
    -0.62
     NYC
    -0.61
    POSITIVE LOGITS
     accuse
    0.97
     accuses
    0.96
     insurgency
    0.95
     militants
    0.93
     separatist
    0.92
     separatists
    0.91
     blamed
    0.90
     insurgents
    0.90
     rebels
    0.90
     militant
    0.88
    Activations Density 1.175%

    No Known Activations