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. 8-RES-JB
    6. 18819
    Prev
    Next
    INDEX
    Explanations

    mentions of physical or metaphorical "runs."

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "run" in multiple contexts

    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
     Hots
    -0.67
     defic
    -0.65
    alam
    -0.64
    ĵĺ
    -0.64
     Males
    -0.62
    omical
    -0.61
     Aires
    -0.60
     defe
    -0.59
     Ink
    -0.59
     Virtue
    -0.58
    POSITIVE LOGITS
    aways
    1.26
    gs
    1.21
    escape
    1.14
    nings
    1.10
    ners
    1.10
    swick
    1.08
    away
    1.06
    ways
    1.01
    estone
    0.93
    dy
    0.93
    Activations Density 0.042%

    No Known Activations