Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 0-RES-JB
    6. 7377
    Prev
    Next
    INDEX
    Explanations

    words related to chasing or pursuit

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "chase" and its variations

    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
     Workers
    -0.65
     democratically
    -0.64
     Lenin
    -0.63
    fell
    -0.63
    RM
    -0.62
     Liter
    -0.62
    Community
    -0.62
     Library
    -0.61
     Rect
    -0.61
     Health
    -0.60
    POSITIVE LOGITS
     chase
    3.98
     chasing
    2.16
     pursuit
    1.98
     chased
    1.95
     hunt
    1.61
     pursue
    1.32
     pursuits
    1.29
     pursu
    1.28
     Chase
    1.27
    hunt
    1.23
    Activations Density 0.007%

    No Known Activations