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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 23192
    Prev
    Next
    INDEX
    Explanations

    mentions of the country "Afghanistan."

    oai_token-act-pair · gpt-3.5-turbo

    mentions and references to Afghanistan

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yss
    -0.83
    vous
    -0.83
    Hunt
    -0.80
    creen
    -0.77
    icles
    -0.74
    */(
    -0.70
    ateur
    -0.68
    ection
    -0.68
    amins
    -0.68
    tainment
    -0.68
    POSITIVE LOGITS
    istan
    1.09
     Afghanistan
    1.08
    ghan
    1.05
     Kabul
    1.04
     Albania
    1.01
     Afghan
    0.99
     Afgh
    0.98
     Taliban
    0.96
     Afghans
    0.94
     Pakistan
    0.84
    Activations Density 0.013%

    No Known Activations