© 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. 10-RES-JB
    11. 10720
    Prev
    Next
    INDEX
    Explanations

    technical terms related to calculations or computations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to calculations and mathematical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oho
    -0.90
    ĪĴ
    -0.78
    unin
    -0.78
    gart
    -0.73
    heimer
    -0.73
    luster
    -0.72
     Misty
    -0.72
    nen
    -0.70
    inki
    -0.68
    ici
    -0.68
    POSITIVE LOGITS
     equations
    1.33
     calculations
    1.21
     calculation
    1.16
     calculating
    1.09
     equation
    1.08
     formulas
    1.08
     math
    0.99
     multiplication
    0.99
     probabilities
    0.98
     Calcul
    0.98
    Activations Density 0.073%

    No Known Activations