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. 11-RES-JB
    6. 16835
    Prev
    Next
    INDEX
    Explanations

    Twitter handles and quotations from NBC news

    oai_token-act-pair · gpt-3.5-turbo

    mentions of news organizations and their programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Riy
    -0.93
    yip
    -0.90
     sword
    -0.89
     Xie
    -0.87
    Sword
    -0.86
     Rim
    -0.83
    Tang
    -0.82
     Tang
    -0.80
    ãĢ
    -0.78
     graphene
    -0.77
    POSITIVE LOGITS
     NBC
    2.15
     CBS
    2.09
    NBC
    2.04
    CBS
    1.97
     Comcast
    1.56
     CNBC
    1.52
     ABC
    1.43
    ABC
    1.40
     Showtime
    1.38
     MSNBC
    1.36
    Activations Density 0.249%

    No Known Activations