© 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. 3-RES-JB
    11. 624
    Prev
    Next
    INDEX
    Explanations

    names, especially the name "Jenkins"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Jenkins."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ccording
    -0.75
    bably
    -0.72
    Interstitial
    -0.71
    ality
    -0.69
    llah
    -0.68
    fare
    -0.67
    Iraq
    -0.66
    igslist
    -0.65
    rontal
    -0.65
    present
    -0.64
    POSITIVE LOGITS
     Jenkins
    1.22
    sey
    0.90
    kins
    0.89
    kinson
    0.80
    haw
    0.80
    bats
    0.78
    ford
    0.77
    etts
    0.77
     Berman
    0.76
    owitz
    0.74
    Activations Density 0.004%

    No Known Activations