© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RES-JB
    11. 23736
    Prev
    Next
    INDEX
    Explanations

    color-related terms, specifically focusing on the color red

    oai_token-act-pair · gpt-3.5-turbo

    references to the color red

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gerald
    -0.92
    SPONSORED
    -0.82
    Ö¼
    -0.76
    =-=-
    -0.74
    OHN
    -0.72
     Lank
    -0.72
    agall
    -0.69
     4090
    -0.69
    Tokens
    -0.69
     Ellis
    -0.68
    POSITIVE LOGITS
    uces
    1.21
    rawn
    1.02
    uced
    1.01
    efined
    1.00
    neck
    1.00
    ucing
    0.99
    irection
    0.95
    der
    0.93
    ouble
    0.92
    oubt
    0.91
    Activations Density 0.019%

    No Known Activations