© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 6634
    Prev
    Next
    INDEX
    Explanations

    legal or regulatory terms related to competition and monopolies

    oai_token-act-pair · gpt-3.5-turbo

    references to antitrust laws and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bray
    -0.75
     strain
    -0.69
    igma
    -0.69
    ahi
    -0.66
     magnification
    -0.65
     rite
    -0.65
     username
    -0.64
     warped
    -0.62
     dimin
    -0.62
     constant
    -0.61
    POSITIVE LOGITS
     antitrust
    2.27
    yg
    1.30
    mun
    1.22
    elope
    1.11
    trust
    1.11
     wiret
    1.03
    rette
    1.02
     Starr
    0.98
     annex
    0.95
    sylvania
    0.94
    Activations Density 0.066%

    No Known Activations