© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16669
    Prev
    Next
    INDEX
    Explanations

    the article "la" in Spanish

    oai_token-act-pair · gpt-3.5-turbo

    the article "la" in various contexts suggesting references to feminine nouns or concepts

    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
    pants
    -0.86
    wolves
    -0.82
    sw
    -0.79
    Sharp
    -0.76
    tons
    -0.72
    sticks
    -0.72
    lessly
    -0.72
    states
    -0.71
    strings
    -0.70
    OLD
    -0.70
    POSITIVE LOGITS
     adolesc
    0.96
    isse
    0.90
     situ
    0.82
    uren
    0.82
     lett
    0.82
     Grande
    0.81
    ÃŁ
    0.78
     cart
    0.78
     facult
    0.77
     mism
    0.77
    Activations Density 0.017%

    No Known Activations