© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 17746
    Prev
    Next
    INDEX
    Explanations

    names, specifically "Rupert"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Rupert Murdoch and related figures in the context of media or news

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assian
    -0.83
    ngth
    -0.75
    activated
    -0.71
     Helsinki
    -0.70
    ccording
    -0.68
    atchewan
    -0.68
    agher
    -0.67
    omething
    -0.67
    href
    -0.66
    pmwiki
    -0.66
    POSITIVE LOGITS
     Murdoch
    1.34
     Rupert
    1.20
    iev
    0.84
    Net
    0.78
    Ru
    0.78
    rey
    0.76
    shire
    0.74
     Hoo
    0.73
    ython
    0.73
     Giles
    0.72
    Activations Density 0.008%

    No Known Activations