Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 1780
    Prev
    Next
    INDEX
    Explanations

    phrases related to net neutrality

    oai_token-act-pair · gpt-3.5-turbo

    terms related to net neutrality and its implications in internet regulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FU
    -0.83
    yon
    -0.75
     Glas
    -0.69
    acca
    -0.69
    iro
    -0.68
     Ful
    -0.67
    Bir
    -0.67
    Pic
    -0.66
     Vor
    -0.66
    Production
    -0.64
    POSITIVE LOGITS
     neutrality
    1.01
     protections
    0.94
     enforcement
    0.84
     rules
    0.83
     safeguards
    0.82
     watchdog
    0.80
     footing
    0.80
     creeps
    0.79
     commissioners
    0.79
     principles
    0.76
    Activations Density 0.015%

    No Known Activations