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. 12-RES-JB
    6. 14594
    Prev
    Next
    INDEX
    Explanations

    mentions of countries, wars, and international relations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to the United States and its global involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uckland
    -0.57
     Cameroon
    -0.54
     Fiji
    -0.53
     Erit
    -0.53
    urat
    -0.53
     Dublin
    -0.52
     Rohing
    -0.52
     Nottingham
    -0.51
     Notting
    -0.51
     cous
    -0.50
    POSITIVE LOGITS
    S
    0.72
     STATES
    0.63
     States
    0.62
     S
    0.58
    %
    0.47
     auto
    0.47
     Auto
    0.47
    %]
    0.46
    Auto
    0.46
    WS
    0.44
    Activations Density 0.155%

    No Known Activations