© 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. 1-RES-JB
    11. 16853
    Prev
    Next
    INDEX
    Explanations

    words related to positions or movements in physical spaces, particularly terms relevant to sports or military maneuvers

    oai_token-act-pair · gpt-3.5-turbo

    terms related to military positioning or strategies

    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
    regulated
    -0.85
     nep
    -0.73
    displayText
    -0.71
    arre
    -0.69
    ccording
    -0.68
     hig
    -0.65
     regulated
    -0.64
     whim
    -0.63
     electronically
    -0.63
     regulate
    -0.63
    POSITIVE LOGITS
    ings
    0.90
    ernel
    0.88
    nuts
    0.87
     Stall
    0.84
    ments
    0.83
    masters
    0.79
    enery
    0.78
    naires
    0.78
    erness
    0.77
    ATURES
    0.77
    Activations Density 0.012%

    No Known Activations