© 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. 1465
    Prev
    Next
    INDEX
    Explanations

    instances of the word "strategy"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of strategies in various contexts

    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
    vals
    -0.77
    rake
    -0.74
    bey
    -0.71
    rd
    -0.71
    oak
    -0.69
    plet
    -0.68
    semble
    -0.67
    export
    -0.67
    ased
    -0.66
    aver
    -0.65
    POSITIVE LOGITS
     strategy
    1.17
    ategy
    1.15
     Strategy
    0.99
     strategies
    0.98
    ategic
    0.93
     strateg
    0.90
     Strategies
    0.85
     formulation
    0.82
     lawy
    0.78
     reversal
    0.75
    Activations Density 0.015%

    No Known Activations