© 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. 9-RES-JB
    11. 11279
    Prev
    Next
    INDEX
    Explanations

    phrases related to axioms or phrases containing the word "ax"

    oai_token-act-pair · gpt-3.5-turbo

    references to axioms and the concept of axiomatic reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Columb
    -0.64
    ATURES
    -0.61
    pants
    -0.61
     Fiscal
    -0.60
    ulton
    -0.60
     Plain
    -0.60
     encour
    -0.57
     Roose
    -0.56
    ĨĴ
    -0.56
    SPONSORED
    -0.55
    POSITIVE LOGITS
    iom
    1.52
    illary
    1.16
    iop
    0.97
    imus
    0.96
    alon
    0.92
    otomy
    0.89
    omatic
    0.88
    ham
    0.87
    ical
    0.86
     ax
    0.85
    Activations Density 0.037%

    No Known Activations