© 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. 23532
    Prev
    Next
    INDEX
    Explanations

    references to countries and regions, particularly focusing on mentions of Croatia and Yugoslavia

    oai_token-act-pair · gpt-3.5-turbo

    references to Croatia and Yugoslavia

    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
    ellation
    -0.80
    lying
    -0.76
    VALUE
    -0.72
    reads
    -0.70
    ENTS
    -0.70
    WARD
    -0.68
     certs
    -0.68
    atives
    -0.67
    ATA
    -0.65
    NING
    -0.64
    POSITIVE LOGITS
     Croatia
    1.11
    Äį
    0.92
    Äĩ
    0.90
    oslov
    0.90
     Herz
    0.89
     Ukrain
    0.83
    ovi
    0.82
     Croatian
    0.81
     Croat
    0.81
    Cro
    0.80
    Activations Density 0.009%

    No Known Activations