© 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. 0-RES-JB
    11. 553
    Prev
    Next
    INDEX
    Explanations

    phrases related to the color green

    oai_token-act-pair · gpt-3.5-turbo

    the term "Green" and related references in sports and environmental contexts

    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
     orphan
    -0.72
     antit
    -0.71
     Fell
    -0.69
     Tiffany
    -0.69
     autop
    -0.67
     proof
    -0.63
     Ep
    -0.63
     innate
    -0.63
     Emb
    -0.63
     Babel
    -0.62
    POSITIVE LOGITS
    Green
    2.37
    Mail
    1.57
    Sports
    1.54
    sports
    1.40
    Conservative
    1.35
    Daily
    1.34
    Sport
    1.21
    Liberal
    1.16
    Games
    1.11
    SF
    1.10
    Activations Density 0.033%

    No Known Activations