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. 9207
    Prev
    Next
    INDEX
    Explanations

    the name "Theresa May"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Theresa May

    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
    DX
    -0.73
    XP
    -0.66
     booster
    -0.65
     endeavor
    -0.65
     meters
    -0.65
     dives
    -0.63
     comp
    -0.61
     meter
    -0.60
    river
    -0.60
     boosters
    -0.59
    POSITIVE LOGITS
     Theresa
    3.74
    resa
    2.49
     Teresa
    1.91
     Brexit
    1.53
    Brexit
    1.51
     Melania
    1.43
     Thatcher
    1.39
     Nicola
    1.36
     Narendra
    1.35
     Angela
    1.32
    Activations Density 0.020%

    No Known Activations