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. 15479
    Prev
    Next
    INDEX
    Explanations

    word sequences related to legal and legislative actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate proposed changes or amendments in legislation

    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
    rete
    -0.72
    UGH
    -0.72
    notice
    -0.71
     sqor
    -0.71
    oad
    -0.69
    ovo
    -0.67
    omatic
    -0.64
    hift
    -0.64
    OX
    -0.63
    live
    -0.63
    POSITIVE LOGITS
     prohibits
    1.20
     forbids
    1.12
     restricts
    1.10
     bans
    1.09
     governs
    1.08
     regulates
    1.05
     seeks
    1.00
     legalized
    0.99
     prevents
    0.97
     decriminal
    0.97
    Activations Density 0.107%

    No Known Activations