© 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. 4-RES-JB
    11. 15314
    Prev
    Next
    INDEX
    Explanations

    specific references to the country "Iraq"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of Iraq and related topics

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

    No Comments

    Negative Logits
    box
    -0.80
    boxes
    -0.78
    alty
    -0.77
    BOOK
    -0.75
    ISTER
    -0.74
    ritch
    -0.72
    SHIP
    -0.71
    Premium
    -0.71
    %%
    -0.69
    bats
    -0.68
    POSITIVE LOGITS
     Hussein
    1.09
    iyah
    1.01
     Kurdistan
    0.93
     Iraq
    0.90
    Iraq
    0.90
     Albania
    0.82
     invaded
    0.82
     Reconstruction
    0.78
    istan
    0.75
    ousing
    0.74
    Activations Density 0.015%

    No Known Activations