© 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. 3-RES-JB
    11. 23945
    Prev
    Next
    INDEX
    Explanations

    information related to numerical data or statistics

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and text patterns that indicate separate thoughts or sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ikuman
    -0.77
     rallying
    -0.64
     immersed
    -0.64
     outl
    -0.64
     community
    -0.63
    icent
    -0.61
    ding
    -0.61
    ãģ®
    -0.60
     metic
    -0.59
     dominated
    -0.59
    POSITIVE LOGITS
     Additionally
    0.81
    catentry
    0.81
     Either
    0.78
     Besides
    0.76
    CLASSIFIED
    0.76
     Ideally
    0.75
     They
    0.75
     Depending
    0.74
     Also
    0.73
     Flavoring
    0.72
    Activations Density 0.062%

    No Known Activations