© 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. 14757
    Prev
    Next
    INDEX
    Explanations

    country names, specifically focusing on Austria

    oai_token-act-pair · gpt-3.5-turbo

    references to Austria and its related terms

    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
    ciples
    -0.91
    Planet
    -0.81
    cipled
    -0.79
    caps
    -0.79
    ear
    -0.77
    elta
    -0.75
    mable
    -0.74
    ever
    -0.74
    transform
    -0.74
    ointed
    -0.73
    POSITIVE LOGITS
     Vienna
    1.06
     Austria
    0.80
     Ãľ
    0.79
     Mellon
    0.76
     Ferdinand
    0.76
     Schwe
    0.75
     Alps
    0.74
    ÃĽ
    0.73
     Austrian
    0.73
     Rothschild
    0.71
    Activations Density 0.009%

    No Known Activations