© 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. 6-RES-JB
    11. 11743
    Prev
    Next
    INDEX
    Explanations

    descriptive language related to colorfulness and vibrancy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    colorful and vibrant descriptions or imagery

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rogen
    -0.84
    psons
    -0.83
    idem
    -0.79
    redit
    -0.78
    QB
    -0.76
    req
    -0.75
    CLA
    -0.74
    olitan
    -0.74
    apist
    -0.72
    anasia
    -0.71
    POSITIVE LOGITS
     colors
    1.13
     colours
    1.12
     Colors
    1.01
     colorful
    0.98
     striped
    0.95
     stripes
    0.94
     dots
    0.93
     colourful
    0.88
     coloured
    0.88
     colored
    0.87
    Activations Density 0.031%

    No Known Activations