© 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. 2179
    Prev
    Next
    INDEX
    Explanations

    phrases marked by punctuation

    oai_token-act-pair · gpt-3.5-turbo

    instances of commas in the text

    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
    aea
    -0.80
    mos
    -0.67
    ¬¼
    -0.66
    idable
    -0.66
    orde
    -0.66
    tsy
    -0.64
    mite
    -0.63
    endo
    -0.61
    =(
    -0.59
    ctl
    -0.59
    POSITIVE LOGITS
     detailing
    1.27
     outlining
    1.23
     wherein
    1.20
     stating
    1.14
     indicating
    1.14
     confirming
    1.13
     revealing
    1.11
     titled
    1.11
     describing
    1.11
     suggesting
    1.11
    Activations Density 0.272%

    No Known Activations