© 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. 2-RES-JB
    11. 8337
    Prev
    Next
    INDEX
    Explanations

    phrases related to regulatory issues

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -1.01
     Sick
    -0.71
     Voy
    -0.70
     Hume
    -0.70
     Locke
    -0.69
     Sleeping
    -0.68
    Bone
    -0.68
     Anniversary
    -0.68
    Liber
    -0.68
     Towns
    -0.67
    POSITIVE LOGITS
     regulators
    1.16
     regulator
    1.12
    assetsadobe
    0.92
    otonin
    0.82
     filings
    0.79
     regulate
    0.78
     agencies
    0.78
     levied
    0.77
     regulating
    0.76
    adeon
    0.75
    Activations Density 0.011%

    No Known Activations