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. 0-RES-JB
    6. 24420
    Prev
    Next
    INDEX
    Explanations

    color-related terms indicating a light or faded shade

    oai_token-act-pair · gpt-3.5-turbo

    references to the color "pale"

    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
     Router
    -0.79
     Controller
    -0.75
     Feedback
    -0.74
    Lot
    -0.73
     Contracts
    -0.72
     Devices
    -0.69
     NCT
    -0.67
    Lock
    -0.67
    Guard
    -0.66
     routers
    -0.65
    POSITIVE LOGITS
     pale
    4.03
     Pale
    2.45
     Paleo
    1.72
     amber
    1.20
     glac
    1.13
     skeletal
    1.07
     faint
    1.05
     crimson
    1.02
    assic
    1.01
     translucent
    1.00
    Activations Density 0.019%

    No Known Activations