© 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. 15434
    Prev
    Next
    INDEX
    Explanations

    numbers representing percentages

    oai_token-act-pair · gpt-3.5-turbo

    percentages related to polling or statistical data

    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
    liga
    -0.76
    ardless
    -0.72
    doors
    -0.72
    shape
    -0.70
    ivating
    -0.68
    folios
    -0.68
    efficients
    -0.68
    redit
    -0.67
    anooga
    -0.66
    raviolet
    -0.64
    POSITIVE LOGITS
    00
    0.79
    370
    0.76
    393
    0.68
    40
    0.67
    mx
    0.67
    th
    0.67
    765
    0.67
    mm
    0.65
    345
    0.64
    MM
    0.64
    Activations Density 0.033%

    No Known Activations