© 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. 2-RES-JB
    11. 12518
    Prev
    Next
    INDEX
    Explanations

    sentences ending with a period and a numeric value 6 or 10

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically full stops or periods

    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
     challeng
    -0.88
     glim
    -0.81
     corrid
    -0.78
     thous
    -0.78
     pse
    -0.76
     referen
    -0.73
     predec
    -0.72
     manif
    -0.71
    wagen
    -0.70
    ãĥ¼ãĥĨ
    -0.70
    POSITIVE LOGITS
    jpg
    0.76
     Serving
    0.73
     Interest
    0.72
     Expand
    0.71
     Includes
    0.71
     Flavoring
    0.69
     Whilst
    0.68
     Specifically
    0.68
     Besides
    0.68
     Since
    0.67
    Activations Density 0.459%

    No Known Activations