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. 336
    Prev
    Next
    INDEX
    Explanations

    mentions of the media mogul Rupert Murdoch

    oai_token-act-pair · gpt-3.5-turbo

    references to Rupert Murdoch and his involvement in media

    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
    CHA
    -0.69
     colors
    -0.65
    fulness
    -0.64
     hyd
    -0.63
     dra
    -0.59
     effectiveness
    -0.59
     performance
    -0.59
     ta
    -0.58
    ace
    -0.58
    ATH
    -0.58
    POSITIVE LOGITS
     Murdoch
    4.36
     Rupert
    1.78
     Bezos
    1.37
     Turnbull
    1.23
     Rothschild
    1.19
     McMahon
    1.19
     tabloid
    1.16
     Thatcher
    1.14
     Rockefeller
    1.14
    kefeller
    1.11
    Activations Density 0.018%

    No Known Activations