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. 12087
    Prev
    Next
    INDEX
    Explanations

    words related to regulations and compliance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to regulatory compliance and standards

    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
    minster
    -0.76
    lest
    -0.73
    Pic
    -0.71
    cellent
    -0.69
    orah
    -0.68
    owicz
    -0.68
    strap
    -0.67
    ilet
    -0.67
    hole
    -0.66
    sonian
    -0.65
    POSITIVE LOGITS
     agencies
    1.10
     filings
    1.04
     oversight
    1.01
     regimes
    1.00
     authority
    0.99
     approvals
    0.98
     authorities
    0.94
     governing
    0.94
     regulators
    0.94
     enforcement
    0.92
    Activations Density 0.014%

    No Known Activations