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. 9-RES-JB
    6. 20996
    Prev
    Next
    INDEX
    Explanations

    statements made by White House Press Secretaries

    oai_token-act-pair · gpt-3.5-turbo

    references to the White House press secretary and related press activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jagu
    -0.96
     Catalan
    -0.94
    Catal
    -0.91
    EStreamFrame
    -0.89
     Catalonia
    -0.86
    Tes
    -0.84
    utra
    -0.84
     glim
    -0.84
    angan
    -0.83
     Catal
    -0.82
    POSITIVE LOGITS
     Obama
    1.38
    Obama
    1.31
     Eisenhower
    1.26
     Barack
    1.22
    OTUS
    1.21
     Washington
    1.18
     Pentagon
    1.18
     HHS
    1.17
    Washington
    1.10
     White
    1.09
    Activations Density 0.717%

    No Known Activations