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. 1-RES-JB
    6. 19943
    Prev
    Next
    INDEX
    Explanations

    references to legal terms, particularly related to copyright law, such as "DMCA" and phrases related to legal actions like "affirmative" and "disengagement"

    oai_token-act-pair · gpt-3.5-turbo

    references to legal agreements or affirmative responses in discussions related to the DMCA

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atility
    -0.77
    uality
    -0.70
    borg
    -0.70
    swick
    -0.69
    rett
    -0.69
    stals
    -0.69
    idays
    -0.68
    IAL
    -0.68
    л
    -0.68
    bats
    -0.68
    POSITIVE LOGITS
     affirmative
    0.80
    BIP
    0.72
    otin
    0.72
    ould
    0.70
    asive
    0.70
    00200000
    0.65
    otropic
    0.65
    ADD
    0.65
    merga
    0.64
     Zeal
    0.63
    Activations Density 0.024%

    No Known Activations