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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-RES-JB
    6. 12979
    Prev
    Next
    INDEX
    Explanations

    mentions of the country Libya

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Libya and related terms

    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
    Premium
    -0.85
    alty
    -0.85
    lasses
    -0.77
    Madison
    -0.75
    icrobial
    -0.74
    TAG
    -0.73
    Seattle
    -0.71
    pressed
    -0.71
    sth
    -0.70
    bilt
    -0.70
    POSITIVE LOGITS
     Libya
    1.18
     Tripoli
    0.95
     Libyan
    0.94
    addafi
    0.89
     Tunisia
    0.85
    ghazi
    0.81
     Albania
    0.81
     militias
    0.78
     Erit
    0.77
     Gaddafi
    0.75
    Activations Density 0.013%

    No Known Activations