© 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. 2-RES-JB
    11. 15004
    Prev
    Next
    INDEX
    Explanations

    percentages expressed numerically

    oai_token-act-pair · gpt-3.5-turbo

    references to statistics and percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pload
    -0.78
    zek
    -0.76
    ãĥ¤
    -0.73
    imir
    -0.72
    ITED
    -0.71
    HCR
    -0.70
    abama
    -0.68
    chn
    -0.68
     obser
    -0.68
    flies
    -0.67
    POSITIVE LOGITS
    percent
    0.87
     percent
    0.82
    imet
    0.79
    rowth
    0.76
    imeter
    0.71
    iles
    0.71
    cake
    0.70
     Percent
    0.68
    lein
    0.68
    eele
    0.67
    Activations Density 0.047%

    No Known Activations