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. 142
    Prev
    Next
    INDEX
    Explanations

    mentions of law enforcement activities, such as police tactics, training, and the use of force

    oai_token-act-pair · gpt-3.5-turbo

    topics related to social issues and their impacts

    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
     caveats
    -0.57
     caveat
    -0.55
    bley
    -0.55
    igel
    -0.52
    erton
    -0.51
    cffffcc
    -0.51
    unts
    -0.51
    hiba
    -0.50
    ECD
    -0.50
     Pwr
    -0.50
    POSITIVE LOGITS
     behalf
    0.60
     various
    0.54
     topics
    0.54
     interact
    0.51
    ãĢij
    0.51
     transgender
    0.51
     upcoming
    0.50
     mater
    0.50
     digital
    0.50
     influ
    0.50
    Activations Density 1.608%

    No Known Activations