© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 4927
    Prev
    Next
    INDEX
    Explanations

    terms related to taking action, strategic thinking, and planning

    oai_token-act-pair · gpt-3.5-turbo

    strategies or actions related to competitive situations or motivations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     attRot
    -0.55
     Hen
    -0.51
    FactoryReloaded
    -0.50
    SSL
    -0.50
     Folk
    -0.49
     Ja
    -0.48
     recent
    -0.47
     cited
    -0.47
    \.
    -0.47
     recount
    -0.45
    POSITIVE LOGITS
     cheaply
    0.93
     efficiently
    0.81
     ASAP
    0.77
     wherever
    0.76
     smarter
    0.75
     responsibly
    0.74
     passively
    0.72
     someday
    0.67
     safely
    0.65
     intellig
    0.65
    Activations Density 1.104%

    No Known Activations