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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 10011
    Prev
    Next
    INDEX
    Explanations

    continental regions or countries

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical regions or continents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elsen
    -0.82
     lett
    -0.73
    mie
    -0.73
    dro
    -0.71
    fts
    -0.70
    phot
    -0.69
    rator
    -0.66
    ppo
    -0.65
    wy
    -0.64
     @@
    -0.64
    POSITIVE LOGITS
     Asia
    1.58
     Africa
    1.46
     Euras
    1.40
    Asia
    1.37
     Americas
    1.33
     Austral
    1.30
     Latin
    1.28
     Caucasus
    1.26
     Balkans
    1.25
     continents
    1.17
    Activations Density 0.129%

    No Known Activations