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. 9-RES-JB
    6. 19327
    Prev
    Next
    INDEX
    Explanations

    requests or petitions for action from government entities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the" and related phrases emphasizing requests or actions directed at authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftime
    -0.75
    TED
    -0.74
    ably
    -0.73
     preceded
    -0.72
    lived
    -0.71
    VERTISEMENT
    -0.70
    terday
    -0.70
    ties
    -0.69
    deals
    -0.69
     namely
    -0.69
    POSITIVE LOGITS
     wealthiest
    1.00
     Legislature
    0.96
     authorities
    0.96
     feds
    0.95
     legislature
    0.93
     slightest
    0.91
     government
    0.91
     chancellor
    0.90
     same
    0.87
     reader
    0.87
    Activations Density 0.212%

    No Known Activations