© 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. 2-RES-JB
    11. 23364
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "squad"

    oai_token-act-pair · gpt-3.5-turbo

    references to sports teams or groups often referred to as squads

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.90
    pire
    -0.74
    lvl
    -0.71
    pport
    -0.69
    ãĥī
    -0.68
    ¿½
    -0.68
    à¼
    -0.65
    RFC
    -0.65
    orgetown
    -0.64
    Cart
    -0.64
    POSITIVE LOGITS
    rons
    1.54
    mates
    1.19
     mates
    1.11
     squads
    0.98
     squad
    0.94
    members
    0.87
    mate
    0.86
    alions
    0.81
    ubs
    0.78
     rosters
    0.77
    Activations Density 0.012%

    No Known Activations