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. 18254
    Prev
    Next
    INDEX
    Explanations

    words related to advisory roles or services

    oai_token-act-pair · gpt-3.5-turbo

    references to advisory roles and committees

    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
     Kinnikuman
    -0.77
    resp
    -0.77
    days
    -0.76
    Ultimate
    -0.74
    Freedom
    -0.73
    Bre
    -0.72
    Pear
    -0.71
    aver
    -0.71
    Ton
    -0.70
    Export
    -0.70
    POSITIVE LOGITS
     advisory
    1.51
     Advisory
    1.16
     advising
    1.03
     advis
    0.98
     Advis
    0.98
     councils
    0.97
     commissions
    0.95
     advise
    0.95
     boards
    0.93
     advisors
    0.89
    Activations Density 0.009%

    No Known Activations