© 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. 10-RES-JB
    11. 18554
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    proper nouns, likely related to people's names or entities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pired
    -0.67
     existed
    -0.63
     exists
    -0.59
     compromises
    -0.57
     subs
    -0.57
    pires
    -0.57
     finds
    -0.57
     hath
    -0.56
    destroy
    -0.56
     doesnt
    -0.56
    POSITIVE LOGITS
    .
    1.03
     sarcast
    0.89
     rhet
    0.77
    .</
    0.76
    _.
    0.75
    .[
    0.74
    .(
    0.72
    .<
    0.71
    ."
    0.71
     via
    0.69
    Activations Density 0.177%

    No Known Activations