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. 8-RES-JB
    6. 18935
    Prev
    Next
    INDEX
    Explanations

    phrases related to geographical locations, particularly countries

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to the political entities of countries or regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    afety
    -0.72
    hern
    -0.69
     therap
    -0.68
    Downloadha
    -0.68
    setting
    -0.68
    acus
    -0.68
    staking
    -0.65
    nery
    -0.65
    netflix
    -0.64
     reper
    -0.64
    POSITIVE LOGITS
     Congo
    0.98
    foundland
    0.92
     Yugoslavia
    0.79
     Macedonia
    0.79
     Territories
    0.77
    Ò
    0.74
     Latvia
    0.73
     Ireland
    0.73
     Nations
    0.73
     Cyprus
    0.73
    Activations Density 0.076%

    No Known Activations