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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 3387
    Prev
    Next
    INDEX
    Explanations

    mentions of laws or regulations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating underlying legal or regulatory frameworks

    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
    è¦ļéĨĴ
    -0.74
    ãĥ£
    -0.67
    0000000000000000
    -0.65
    iferation
    -0.64
    atial
    -0.64
    ãĥīãĥ©ãĤ´ãĥ³
    -0.61
    éŃĶ
    -0.61
     Geo
    -0.60
     distinctly
    -0.60
     nearby
    -0.60
    POSITIVE LOGITS
    neath
    1.09
    graduate
    0.89
    pins
    0.85
    comings
    0.84
    ntil
    0.82
    tain
    0.81
    pants
    0.80
    stant
    0.79
    itled
    0.76
    rated
    0.76
    Activations Density 0.008%

    No Known Activations