© 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 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. 0-RES-JB
    11. 12576
    Prev
    Next
    INDEX
    Explanations

    the word "Tex" with varying numerical suffixes

    oai_token-act-pair · gpt-3.5-turbo

    references to the Tex and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Warwick
    -0.79
     Chak
    -0.79
     Potter
    -0.77
     Sweeney
    -0.74
     Kimmel
    -0.74
     Schwartz
    -0.74
    mble
    -0.71
    adder
    -0.70
     Lego
    -0.70
     ADHD
    -0.69
    POSITIVE LOGITS
    tex
    3.96
    Tex
    3.09
     Tex
    2.84
     tex
    2.62
    TeX
    1.60
    tec
    1.29
    Texas
    1.26
    tx
    1.19
    TX
    1.13
     TX
    1.04
    Activations Density 0.053%

    No Known Activations