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. 1-RES-JB
    6. 18626
    Prev
    Next
    INDEX
    Explanations

    mentions of the country "Serbia."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Serbia and Serbian-related terms

    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
    sworth
    -0.89
    ership
    -0.89
    shaw
    -0.83
    ORGE
    -0.81
    ITNESS
    -0.77
    aday
    -0.76
    intosh
    -0.76
    VERTISEMENT
    -0.75
    ARR
    -0.74
    enegger
    -0.74
    POSITIVE LOGITS
     mosqu
    1.01
     Serbia
    0.99
     Serbian
    0.85
    Äį
    0.78
     Chal
    0.75
    angel
    0.74
    ãĤ®
    0.71
     Leban
    0.71
     Nikola
    0.71
    inite
    0.69
    Activations Density 0.016%

    No Known Activations