© 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. 4-RES-JB
    11. 12289
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific industries or technical terms such as "excise tax" or "anthropologists"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to societal issues and legal matters

    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
    Ô
    -0.72
    ara
    -0.68
    ategor
    -0.66
    rss
    -0.64
    Commerce
    -0.63
    ãĥķãĤ©
    -0.61
    hots
    -0.61
     ..........
    -0.61
     âĢº
    -0.61
     Disorder
    -0.60
    POSITIVE LOGITS
    liest
    0.95
     portion
    0.90
     itself
    0.88
    iest
    0.88
     element
    0.83
     equivalents
    0.78
    ultimate
    0.76
    osphere
    0.75
     rul
    0.75
    cients
    0.74
    Activations Density 0.902%

    No Known Activations