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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2-RES-JB
    6. 20513
    Prev
    Next
    INDEX
    Explanations

    mentions of the country Estonia

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Estonia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rooms
    -0.76
    cules
    -0.70
    illas
    -0.69
    loads
    -0.68
    aird
    -0.68
    esome
    -0.67
    patch
    -0.66
    cause
    -0.65
    Ward
    -0.64
    =-=-=-=-=-=-=-=-
    -0.64
    POSITIVE LOGITS
     Eston
    0.87
     Estonia
    0.87
     Finland
    0.76
    ¬¼
    0.74
     Nadu
    0.74
     Bundes
    0.72
     Defence
    0.71
     Latvia
    0.70
     Bok
    0.69
    rolet
    0.67
    Activations Density 0.010%

    No Known Activations