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. 7-RES-JB
    6. 9225
    Prev
    Next
    INDEX
    Explanations

    words related to the country Poland

    oai_token-act-pair · gpt-3.5-turbo

    references to Poland and Polish identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ouston
    -0.82
    querque
    -0.79
    inous
    -0.79
    rian
    -0.77
    hematically
    -0.76
    rians
    -0.74
    wered
    -0.73
    rees
    -0.72
    ---------------
    -0.72
     Rockefeller
    -0.71
    POSITIVE LOGITS
    ÅĤ
    0.95
     Pact
    0.92
    oslov
    0.73
     Mehran
    0.73
     Poland
    0.71
    anski
    0.71
     Warsaw
    0.70
    inski
    0.70
    é»Ĵ
    0.69
     Osw
    0.67
    Activations Density 0.025%

    No Known Activations