© 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. 13932
    Prev
    Next
    INDEX
    Explanations

    the name "ans" or variations thereof in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "answers" or terms related to responses and inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    •ans
    #2 activation: 28.16

    No Comments

    Negative Logits
    ptive
    -0.80
    ADS
    -0.77
    fell
    -0.62
     Bezos
    -0.60
     buds
    -0.59
    ptives
    -0.59
    lled
    -0.57
    SIGN
    -0.57
     Kem
    -0.56
     WATCHED
    -0.55
    POSITIVE LOGITS
    hee
    1.10
    ullivan
    1.04
    laughter
    0.97
    chwitz
    0.94
    hu
    0.91
    avage
    0.88
    olini
    0.82
    hao
    0.82
    poon
    0.82
    WER
    0.82
    Activations Density 0.023%

    No Known Activations