© 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. 8-RES-JB
    11. 19329
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Tex" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to Texas and related cultural elements or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ding
    -0.74
    ski
    -0.72
    ersen
    -0.71
    icum
    -0.67
    wear
    -0.67
    icably
    -0.67
    igree
    -0.66
    deen
    -0.64
    uster
    -0.64
     livest
    -0.63
    POSITIVE LOGITS
    ij士
    0.86
    xon
    0.83
    Mex
    0.82
     Tex
    0.80
     Mex
    0.80
    otle
    0.79
    Lay
    0.76
    cellent
    0.76
    veland
    0.75
     Vald
    0.71
    Activations Density 0.085%

    No Known Activations