© 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. 3135
    Prev
    Next
    INDEX
    Explanations

    instances of the word "who"

    oai_token-act-pair · gpt-3.5-turbo

    references to the interrogative word "who."

    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
    Not in Any Lists

    No Comments

    Negative Logits
    framework
    -0.69
     guiActiveUnfocused
    -0.66
    ranging
    -0.66
    eme
    -0.65
    OME
    -0.61
    tnc
    -0.61
    GV
    -0.60
     Inquiry
    -0.58
    strip
    -0.58
     suggestive
    -0.57
    POSITIVE LOGITS
     else
    1.19
     owns
    1.17
    soever
    1.03
     cares
    1.02
     knows
    1.00
     owes
    0.98
    oping
    0.98
     pays
    0.97
     occupies
    0.95
     participates
    0.95
    Activations Density 0.047%

    No Known Activations