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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 1738
    Prev
    Next
    INDEX
    Explanations

    phrases related to the efficient or inefficient use of resources or time

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of wastefulness, particularly concerning the use of resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MODE
    -0.67
     Outbreak
    -0.63
    oland
    -0.63
    sit
    -0.62
     haunted
    -0.61
    wolves
    -0.61
    boxing
    -0.61
    sort
    -0.59
    weather
    -0.59
    ectomy
    -0.57
    POSITIVE LOGITS
     money
    1.66
     funds
    1.50
     dollars
    1.50
    money
    1.39
     Dollars
    1.38
     resources
    1.33
     bucks
    1.28
     Money
    1.26
     cash
    1.25
     taxpayer
    1.21
    Activations Density 0.885%

    No Known Activations