© 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. 3-RES-JB
    11. 10630
    Prev
    Next
    INDEX
    Explanations

    mentions of countries or nationalities, particularly focusing on Lithuania or Luxembourg

    oai_token-act-pair · gpt-3.5-turbo

    references to Lithuania and Luxembourg within the context of music and culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fare
    -0.84
    older
    -0.79
    ctive
    -0.78
    wh
    -0.76
    selage
    -0.76
    pite
    -0.74
    manac
    -0.74
    <<
    -0.71
    sworth
    -0.70
    bler
    -0.69
    POSITIVE LOGITS
    oslov
    0.99
     Malta
    0.97
    etsk
    0.89
     Latvia
    0.88
     Luxembourg
    0.87
     Slovenia
    0.82
     Lithuania
    0.80
     Cyprus
    0.78
    uania
    0.76
     Slovakia
    0.76
    Activations Density 0.015%

    No Known Activations