© 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. 9-RES-JB
    11. 17744
    Prev
    Next
    INDEX
    Explanations

    phrases related to someone speaking or asserting

    oai_token-act-pair · gpt-3.5-turbo

    pronouns, particularly focusing on "he" and "she" in the context of dialogue or statements

    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
     Royale
    -0.65
     Defence
    -0.63
    Inc
    -0.62
     Grid
    -0.62
     internationally
    -0.61
     Berk
    -0.60
    Category
    -0.59
     Azerb
    -0.59
     HG
    -0.57
     Front
    -0.56
    POSITIVE LOGITS
    uristic
    0.97
    eded
    0.86
    lder
    0.86
    mos
    0.85
    zbollah
    0.84
    gemony
    0.83
    iple
    0.81
    ctor
    0.79
    aped
    0.78
     didnt
    0.76
    Activations Density 0.064%

    No Known Activations