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. 3-RES-JB
    6. 8083
    Prev
    Next
    INDEX
    Explanations

    keywords related to strategic decision-making

    oai_token-act-pair · gpt-3.5-turbo

    explicit references to strategies or plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rake
    -0.81
    plet
    -0.74
    ippers
    -0.70
    bey
    -0.70
    azar
    -0.69
    vals
    -0.68
    oak
    -0.68
    owan
    -0.66
    rd
    -0.66
    gur
    -0.66
    POSITIVE LOGITS
    ategy
    1.09
     strategy
    1.04
     Strategy
    0.93
    ategic
    0.89
     formulation
    0.87
     strategies
    0.87
     strateg
    0.80
     Strategies
    0.77
    oleon
    0.76
     reversal
    0.74
    Activations Density 0.017%

    No Known Activations