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. 1-RES-JB
    6. 17765
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific group or team, specifically "squad."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "squad" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.86
    à¼
    -0.76
    pire
    -0.75
    JUST
    -0.71
    flame
    -0.69
    tale
    -0.69
    ãĥī
    -0.68
    Cart
    -0.68
    pport
    -0.66
    orgetown
    -0.65
    POSITIVE LOGITS
    rons
    1.35
     squads
    1.23
     squad
    1.21
     mates
    1.08
    mates
    1.02
    alions
    0.87
     rosters
    0.85
     Squad
    0.83
     uniforms
    0.80
     favourites
    0.77
    Activations Density 0.008%

    No Known Activations