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. 7-RES-JB
    6. 3403
    Prev
    Next
    INDEX
    Explanations

    texts related to strategic planning in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of strategies or plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ournal
    -0.80
    phe
    -0.75
    ividual
    -0.74
    izens
    -0.73
     Presence
    -0.71
    deen
    -0.70
    hal
    -0.68
    abytes
    -0.67
     Visitors
    -0.66
     Recording
    -0.66
    POSITIVE LOGITS
     devised
    1.03
     whereby
    0.98
     practiced
    0.92
     aimed
    0.89
     implemented
    0.88
     designed
    0.82
     pioneered
    0.82
     undertaken
    0.80
     underway
    0.79
     aiming
    0.77
    Activations Density 0.646%

    No Known Activations