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

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 1404
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal cases or investigations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various types of diseases and medical conditions

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

    No Comments

    Negative Logits
    ersive
    -0.90
    ãĤ©
    -0.83
    enegger
    -0.79
    ¥ŀ
    -0.77
     Cosponsors
    -0.74
    arious
    -0.74
    è¦ļéĨĴ
    -0.74
    natureconservancy
    -0.73
    assium
    -0.73
    osponsors
    -0.72
    POSITIVE LOGITS
    xual
    1.69
    hift
    0.85
    lly
    0.80
     inhibitors
    0.78
    ño
    0.78
    ñ
    0.73
    eer
    0.73
    ase
    0.72
    construct
    0.71
    asing
    0.70
    Activations Density 0.014%

    No Known Activations