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. 24413
    Prev
    Next
    INDEX
    Explanations

    official titles or positions with the term "Deputy."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "duty" and its variations related to responsibilities or roles

    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
    suit
    -0.85
    Champ
    -0.83
    matic
    -0.78
    ebook
    -0.77
    suits
    -0.76
    Drive
    -0.76
    lake
    -0.75
    ±
    -0.73
    hot
    -0.73
    Jump
    -0.73
    POSITIVE LOGITS
    uty
    1.14
     informant
    0.81
     Investigator
    0.76
     Sgt
    0.74
     conclud
    0.73
     citiz
    0.72
     Azerb
    0.71
     Inspector
    0.71
    geant
    0.71
     describ
    0.71
    Activations Density 0.037%

    No Known Activations