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. 4352
    Prev
    Next
    INDEX
    Explanations

    keywords related to control and management

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "control."

    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
    gow
    -0.77
    istle
    -0.70
    tein
    -0.70
    ich
    -0.68
     Honour
    -0.64
     Beir
    -0.63
    htt
    -0.62
    iscopal
    -0.61
    odic
    -0.61
    atre
    -0.61
    POSITIVE LOGITS
     freak
    0.87
     levers
    0.81
     valve
    0.79
    eer
    0.78
     valves
    0.77
     exercised
    0.77
    eering
    0.76
    orate
    0.76
     fre
    0.73
    ulators
    0.73
    Activations Density 0.054%

    No Known Activations