© 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. 9-RES-JB
    11. 7012
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements in texts

    oai_token-act-pair · gpt-3.5-turbo

    quantitative comparisons and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vana
    -0.56
     laz
    -0.54
    agara
    -0.54
     recre
    -0.53
    rology
    -0.52
    henko
    -0.52
     orally
    -0.52
     flashed
    -0.52
    overe
    -0.51
     commenced
    -0.51
    POSITIVE LOGITS
    %.
    1.04
     margins
    0.97
     margin
    0.95
     thirds
    0.88
     factor
    0.87
     percentage
    0.85
    %,
    0.84
    %;
    0.82
    dB
    0.78
    %"
    0.75
    Activations Density 0.129%

    No Known Activations