© 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. 0-RES-JB
    11. 6276
    Prev
    Next
    INDEX
    Explanations

    proper nouns starting with the word "Blue"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Blue."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     persecut
    -0.81
    ËĪ
    -0.78
    imil
    -0.77
    Iraq
    -0.67
    enegger
    -0.66
     respons
    -0.65
     includ
    -0.65
    esses
    -0.65
     persecution
    -0.64
    endix
    -0.64
    POSITIVE LOGITS
     Blue
    3.61
    Blue
    2.97
    blue
    2.27
     blue
    2.20
     Purple
    1.96
     Yellow
    1.95
     Red
    1.69
     Blues
    1.66
     Green
    1.66
    Yellow
    1.56
    Activations Density 0.013%

    No Known Activations