© 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. 4-RES-JB
    11. 3554
    Prev
    Next
    INDEX
    Explanations

    data measurement relationships or statistics, particularly ratios or proportions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating proportions or statistical distributions

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

    No Comments

    Negative Logits
    arthy
    -0.75
    ustomed
    -0.69
    aido
    -0.68
    andise
    -0.67
    nance
    -0.65
    ynt
    -0.65
    ipel
    -0.64
    enance
    -0.64
    lished
    -0.63
    wordpress
    -0.63
    POSITIVE LOGITS
     Sins
    0.69
    877
    0.67
    683
    0.65
     circle
    0.64
     circles
    0.64
     uphill
    0.64
     taco
    0.63
    4
    0.62
    5
    0.62
    8
    0.61
    Activations Density 0.145%

    No Known Activations