© 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. 6-RES-JB
    11. 11787
    Prev
    Next
    INDEX
    Explanations

    programming syntax related to assignments and comparisons

    oai_token-act-pair · gpt-3.5-turbo

    programming syntax or structures related to functions and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iple
    -0.87
    olls
    -0.74
    yright
    -0.74
    lasses
    -0.74
    mble
    -0.73
    ernel
    -0.73
    rawl
    -0.72
    lene
    -0.72
    vae
    -0.72
    aspers
    -0.70
    POSITIVE LOGITS
     {"
    0.84
     Ùħ
    0.79
     nil
    0.72
     اÙĦ
    0.72
     ({
    0.70
     Ø
    0.70
     Mongo
    0.68
     Became
    0.67
     Array
    0.66
     Taj
    0.65
    Activations Density 0.007%

    No Known Activations