© 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. 0-RES-JB
    11. 22739
    Prev
    Next
    INDEX
    Explanations

    the word "insurgents"

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to insurgent groups and conflict

    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
    lot
    -0.75
    Jer
    -0.74
     Frozen
    -0.74
     Torah
    -0.73
     Deck
    -0.71
    Cos
    -0.70
     Pier
    -0.70
    Touch
    -0.70
    ce
    -0.69
     Comet
    -0.69
    POSITIVE LOGITS
     insurgents
    3.26
     insurgent
    2.92
     insurgency
    2.79
     insurg
    2.19
     insurrection
    1.53
     guerrilla
    1.47
     Taliban
    1.36
     militants
    1.29
     Afghans
    1.29
     separatists
    1.22
    Activations Density 0.020%

    No Known Activations