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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 7453
    Prev
    Next
    INDEX
    Explanations

    countries or geographic locations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific countries, particularly Belarus and Azerbaijan

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    perse
    -0.79
    vantage
    -0.78
    ORGE
    -0.74
    latable
    -0.72
    athed
    -0.71
    abolic
    -0.70
    achers
    -0.70
    ciation
    -0.70
    nery
    -0.70
    Kin
    -0.68
    POSITIVE LOGITS
    insk
    0.87
     Bots
    0.76
     Belarus
    0.74
     pupp
    0.69
     resid
    0.68
     capit
    0.67
     resp
    0.67
    kers
    0.65
    âĸĪ
    0.64
    ansas
    0.63
    Activations Density 0.023%

    No Known Activations