© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 16712
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "they" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dear
    -0.73
     è£ıè
    -0.72
     Alas
    -0.69
    âĦ¢:
    -0.65
     Indeed
    -0.64
     Recall
    -0.61
    ãĤ´ãĥ³
    -0.61
    YES
    -0.61
    DAY
    -0.60
    WARE
    -0.60
    POSITIVE LOGITS
    're
    1.16
     ain
    1.05
    've
    1.03
     [
    1.02
     gotta
    0.96
    'll
    0.96
     didn
    0.93
     really
    0.93
     kind
    0.91
     definitely
    0.88
    Activations Density 0.458%

    No Known Activations