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. 4548
    Prev
    Next
    INDEX
    Explanations

    names or titles related to leadership or authority roles

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals holding the title of "Chief" in various professional contexts

    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
     PLUS
    -0.75
    inav
    -0.67
    isphere
    -0.65
    apy
    -0.64
    ificate
    -0.64
    apon
    -0.63
     placebo
    -0.61
    âĶĢâĶĢâĶĢâĶĢ
    -0.61
     extras
    -0.61
    liga
    -0.60
    POSITIVE LOGITS
     Chief
    3.64
    Chief
    2.97
     chief
    2.47
    chief
    2.18
     chiefs
    1.81
     Deputy
    1.71
     Chiefs
    1.69
     Superintendent
    1.66
     Chairman
    1.66
     Principal
    1.62
    Activations Density 0.008%

    No Known Activations