© 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. 11-RES-JB
    11. 6709
    Prev
    Next
    INDEX
    Explanations

    specific punctuation patterns, identifying phrases or sentences that end with a semi-colon followed immediately by a number

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly semicolons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inki
    -0.73
    edo
    -0.73
    frac
    -0.71
    ema
    -0.70
    ãĥĥãĥĪ
    -0.70
    unda
    -0.69
    IDENT
    -0.69
    stration
    -0.69
    Accessory
    -0.68
    ells
    -0.67
    POSITIVE LOGITS
     moreover
    1.61
     furthermore
    1.49
     however
    1.41
     meanwhile
    1.34
     nevertheless
    1.30
     hence
    1.30
     consequently
    1.29
     indeed
    1.25
     namely
    1.24
     alternatively
    1.23
    Activations Density 0.062%

    No Known Activations