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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7-RES-JB
    11. 14441
    Prev
    Next
    INDEX
    Explanations

    color-related terms

    oai_token-act-pair · gpt-3.5-turbo

    color names and their associations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issance
    -0.57
    resy
    -0.55
    "))
    -0.54
    ciplinary
    -0.52
    itivity
    -0.50
    depending
    -0.49
    ournals
    -0.47
    erness
    -0.47
    iblical
    -0.45
     Practices
    -0.45
    POSITIVE LOGITS
    âĨĴ
    0.55
     versus
    0.54
     vs
    0.52
     =>
    0.51
     ($)
    0.50
     âĨĴ
    0.50
    ®,
    0.49
     ($
    0.48
    Äĵ
    0.47
    =>
    0.47
    Activations Density 1.334%

    No Known Activations