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. 2-RES-JB
    6. 20601
    Prev
    Next
    INDEX
    Explanations

    instances of the word "authority."

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lovely
    -0.78
     Resist
    -0.76
     Shal
    -0.75
     Leica
    -0.71
    Lens
    -0.68
    Ale
    -0.67
     Taste
    -0.65
     Indust
    -0.63
     Schwar
    -0.63
     Alto
    -0.63
    POSITIVE LOGITS
     authority
    1.26
    Reviewer
    1.04
     delegated
    0.93
     vested
    0.89
     conferred
    0.86
     nomine
    0.85
    authorized
    0.83
     confir
    0.82
    ignty
    0.80
     authorities
    0.78
    Activations Density 0.010%

    No Known Activations