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. 9-RES-JB
    6. 6252
    Prev
    Next
    INDEX
    Explanations

    phrases related to working hard and taking action to achieve certain goals or improve various aspects

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "to" followed by verbs indicating actions or efforts

    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
     Used
    -0.65
     Cust
    -0.63
     Klu
    -0.62
     hairs
    -0.62
     Thoughts
    -0.62
     pandemonium
    -0.62
     Rai
    -0.61
     Perspective
    -0.60
    quickShipAvailable
    -0.60
    Analysis
    -0.60
    POSITIVE LOGITS
     ensure
    1.46
     minimize
    1.37
     improve
    1.35
     educate
    1.31
     maximize
    1.31
     promote
    1.31
     achieve
    1.26
     optimize
    1.25
     eradicate
    1.21
     assure
    1.21
    Activations Density 0.176%

    No Known Activations