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. 4-RES-JB
    6. 18897
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to the color purple

    oai_token-act-pair · gpt-3.5-turbo

    references to the color purple and its variants

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

    No Comments

    Negative Logits
    76561
    -0.78
    LER
    -0.78
    çīĪ
    -0.74
    ETF
    -0.74
     Heller
    -0.72
    APD
    -0.71
    hematic
    -0.71
    ör
    -0.71
     Gutenberg
    -0.70
    ITNESS
    -0.69
    POSITIVE LOGITS
     velvet
    0.91
     dye
    0.88
     purple
    0.85
    tail
    0.85
     Purple
    0.81
     violet
    0.79
     ink
    0.79
     cabbage
    0.77
     hue
    0.76
     triangle
    0.76
    Activations Density 0.007%

    No Known Activations