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

    Neuronpedia

    APICircuit 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. 11-RES-JB
    6. 8333
    Prev
    Next
    INDEX
    Explanations

    material and texture descriptions related to natural elements like plants, rocks, and animals

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to color and texture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     variance
    -0.80
     administrative
    -0.78
     exceptions
    -0.76
     Andromeda
    -0.76
     Hell
    -0.76
     appropriation
    -0.75
     totality
    -0.74
     uncertainties
    -0.74
     credit
    -0.74
     Nass
    -0.73
    POSITIVE LOGITS
    shaped
    1.96
    covered
    1.85
    colored
    1.81
    sized
    1.81
    skinned
    1.74
    lined
    1.68
    filled
    1.66
    eyed
    1.65
    haired
    1.64
    clad
    1.60
    Activations Density 0.084%

    No Known Activations