© 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. 2918
    Prev
    Next
    INDEX
    Explanations

    references to the term "Blue"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Blue" in various contexts

    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
     rounded
    -0.79
     cann
    -0.73
     judgment
    -0.68
     Medic
    -0.67
     present
    -0.66
     passers
    -0.65
     capt
    -0.65
     deserved
    -0.64
     pont
    -0.64
     bonded
    -0.64
    POSITIVE LOGITS
    Blue
    3.03
    blue
    2.95
    Red
    1.69
    Yellow
    1.32
    Gray
    1.20
    Pink
    1.17
    Grey
    1.17
    RED
    1.14
    red
    1.12
    orange
    1.11
    Activations Density 0.016%

    No Known Activations