© 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. 9-RES-JB
    11. 1901
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements and numerical comparisons

    oai_token-act-pair · gpt-3.5-turbo

    statistical data and numeric measurements

    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
    :,
    -0.62
    ():
    -0.58
    aryl
    -0.58
    rive
    -0.56
    anners
    -0.55
    ourning
    -0.54
     ('
    -0.54
     jo
    -0.54
    redd
    -0.53
     âĵĺ
    -0.53
    POSITIVE LOGITS
     compared
    0.79
    actly
    0.78
     equivalent
    0.75
     fraction
    0.69
    phabet
    0.66
     deviation
    0.66
     times
    0.66
     deviations
    0.65
     enough
    0.64
    %).
    0.64
    Activations Density 0.247%

    No Known Activations