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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-RES-JB
    6. 12304
    Prev
    Next
    INDEX
    Explanations

    proper names of people and places

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to sports events and player movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     federally
    -0.87
     behavior
    -0.85
     nonpartisan
    -0.84
     solic
    -0.81
     civ
    -0.80
     behaviors
    -0.79
     subsidized
    -0.79
     digit
    -0.78
     lava
    -0.78
     polarization
    -0.77
    POSITIVE LOGITS
    England
    1.58
    Arsenal
    1.50
    Liverpool
    1.47
    However
    1.39
    Players
    1.39
    Coach
    1.38
    Having
    1.37
    Asked
    1.35
    Manchester
    1.33
    Football
    1.31
    Activations Density 0.197%

    No Known Activations