Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 4687
    Prev
    Next
    INDEX
    Explanations

    phrases related to the color crimson

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Crimson" and its variations, indicating a focus on the University of Alabama and related cultural elements

    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
     Pod
    -0.81
    eur
    -0.79
    tel
    -0.79
    Wheel
    -0.77
    manuel
    -0.77
    arest
    -0.74
    Dutch
    -0.74
    forward
    -0.72
    mp
    -0.72
    payer
    -0.72
    POSITIVE LOGITS
     Crimson
    4.09
     Tide
    1.60
    crim
    1.53
     crimson
    1.46
     Sapphire
    1.31
     Saban
    1.25
     Crim
    1.24
    usc
    1.22
     Hoover
    1.20
     Coral
    1.15
    Activations Density 0.056%

    No Known Activations