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. 1-RES-JB
    6. 9845
    Prev
    Next
    INDEX
    Explanations

    names or terms related to people in positions who have stepped down from their roles

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "resigned."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oos
    -0.74
    Lex
    -0.68
    arkin
    -0.64
     Glob
    -0.64
    rodu
    -0.63
    liv
    -0.63
    gat
    -0.62
    APH
    -0.62
    orig
    -0.62
    FORE
    -0.61
    POSITIVE LOGITS
     resigned
    1.29
     resignation
    1.11
     resign
    1.08
    ptin
    0.83
    icter
    0.81
    escent
    0.81
    terness
    0.78
     quitting
    0.75
    istant
    0.73
     srfAttach
    0.72
    Activations Density 0.004%

    No Known Activations