© 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. 6-RES-JB
    11. 14708
    Prev
    Next
    INDEX
    Explanations

    dates expressed in a specific format (e.g., "16:9" or "16:10")

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical values, particularly those involving the number 16

    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
    olicy
    -0.96
     tremend
    -0.88
    isode
    -0.83
    atre
    -0.83
    uppet
    -0.82
    enhagen
    -0.78
    etsk
    -0.76
    andise
    -0.75
    pherd
    -0.75
    rint
    -0.75
    POSITIVE LOGITS
    384
    1.29
    6666
    1.20
    th
    0.92
    05
    0.87
    07
    0.86
    650
    0.85
    06
    0.84
    03
    0.83
    teen
    0.83
    09
    0.82
    Activations Density 0.038%

    No Known Activations