© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3370
    Prev
    Next
    INDEX
    Explanations

    mathematical or programming terms related to operators and operands

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mathematical operations and operators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.74
    USER
    -0.69
     marsh
    -0.68
     spotting
    -0.63
     Heller
    -0.60
     Pradesh
    -0.59
     vengeance
    -0.58
     Hawaiian
    -0.57
     CARD
    -0.57
    esville
    -0.56
    POSITIVE LOGITS
    ators
    1.50
    ating
    1.38
    ational
    1.38
    andi
    1.30
    ator
    1.28
    ations
    1.28
    ates
    1.20
    atives
    1.17
    atin
    1.15
    atic
    1.13
    Activations Density 0.048%

    No Known Activations