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. 4-RES-JB
    6. 22808
    Prev
    Next
    INDEX
    Explanations

    mentions of legal rulings and political events related to controversial topics

    oai_token-act-pair · gpt-3.5-turbo

    significant legal rulings and governmental decisions

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

    No Comments

    Negative Logits
     [/
    -0.56
     FANTASY
    -0.52
     Morty
    -0.51
    .--
    -0.51
    [/
    -0.49
    !'
    -0.48
     âĶľâĶĢâĶĢ
    -0.48
     moreover
    -0.47
     depends
    -0.47
     Magicka
    -0.47
    POSITIVE LOGITS
     inaugural
    0.50
    çͰ
    0.49
     inauguration
    0.49
     Hurricane
    0.48
     vacated
    0.47
     ratification
    0.45
     namesake
    0.44
     undisclosed
    0.44
    election
    0.44
    Reilly
    0.43
    Activations Density 3.359%

    No Known Activations