© 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. 1-RES-JB
    11. 20663
    Prev
    Next
    INDEX
    Explanations

    mentions of the country Libya

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Libya and related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    older
    -0.87
    lasses
    -0.80
    due
    -0.79
    ¤
    -0.75
    shr
    -0.73
    aic
    -0.73
    sth
    -0.72
    Premium
    -0.72
    laus
    -0.71
    hate
    -0.70
    POSITIVE LOGITS
     Libya
    1.38
     Tripoli
    1.08
     Libyan
    1.07
    addafi
    0.96
     Tunisia
    0.93
    ghazi
    0.92
     Gaddafi
    0.89
     militias
    0.87
    ombo
    0.83
     Mubarak
    0.81
    Activations Density 0.006%

    No Known Activations