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

    Neuronpedia

    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. 0-RES-JB
    11. 15428
    Prev
    Next
    INDEX
    Explanations

    words related to motivating or stimulating action or change

    oai_token-act-pair · gpt-3.5-turbo

    the word "spur" and its variations indicating initiation or encouragement of an action or process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GC
    -0.70
    Meta
    -0.67
    aware
    -0.67
     Authentication
    -0.66
    metics
    -0.66
     Identity
    -0.65
     hierarchy
    -0.63
    Login
    -0.63
    Console
    -0.61
    hern
    -0.60
    POSITIVE LOGITS
     spur
    4.08
     stimulate
    1.32
     Spur
    1.25
     spark
    1.19
     spurred
    1.18
     stimulating
    1.03
     incent
    0.98
     impetus
    0.95
     stimulated
    0.94
     spike
    0.93
    Activations Density 0.014%

    No Known Activations