© 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. 20880
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and terms related to mathematical calculations

    oai_token-act-pair · gpt-3.5-turbo

    mathematical terms and concepts related to equations

    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
    ulhu
    -0.65
    âĢ¢âĢ¢
    -0.65
    âĹ¼
    -0.65
    utsche
    -0.62
    berman
    -0.62
    entious
    -0.62
    ogg
    -0.62
    vik
    -0.62
    aina
    -0.61
    eco
    -0.61
    POSITIVE LOGITS
     equation
    1.19
     equations
    1.08
    idian
    0.85
     coefficients
    0.76
     calculus
    0.74
     formula
    0.71
    ysis
    0.70
     formulas
    0.69
    eering
    0.68
    cles
    0.68
    Activations Density 0.009%

    No Known Activations