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. 0-RES-JB
    6. 23779
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to Malcolm Turnbull

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     honor
    -0.72
     theater
    -0.64
    POST
    -0.64
     honored
    -0.64
    --
    -0.62
     freed
    -0.62
     phantom
    -0.62
     training
    -0.61
     controller
    -0.60
     ....
    -0.60
    POSITIVE LOGITS
     Turnbull
    3.83
     Abbott
    1.63
     Trudeau
    1.49
     Rudd
    1.42
     NBN
    1.41
    Austral
    1.41
     Canberra
    1.38
     Murdoch
    1.37
     Farage
    1.35
     Tasman
    1.31
    Activations Density 0.014%

    No Known Activations