© 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. 11-RES-JB
    11. 4952
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to a specific subject

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and their associations with actions or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å½
    -0.50
     Golden
    -0.47
     Friendly
    -0.46
     Westminster
    -0.45
     Five
    -0.45
     Dayton
    -0.45
     Eighth
    -0.45
    GROUND
    -0.45
    ————————
    -0.44
    FUL
    -0.44
    POSITIVE LOGITS
     doesnt
    1.05
     seems
    0.93
    alian
    0.93
     depends
    0.92
     ain
    0.91
     hurts
    0.90
     involves
    0.90
     contains
    0.89
    's
    0.89
     boils
    0.87
    Activations Density 0.274%

    No Known Activations