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. 11-RES-JB
    6. 17885
    Prev
    Next
    INDEX
    Explanations

    phrases related to safety precautions

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation and patterns suggesting conclusion or completion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     waged
    -0.70
     alleged
    -0.69
     compelled
    -0.67
     outraged
    -0.67
     inference
    -0.66
     unprecedented
    -0.66
     subsystem
    -0.66
     unrem
    -0.65
     satell
    -0.65
     sustained
    -0.65
    POSITIVE LOGITS
     Alternatively
    1.54
     Otherwise
    1.43
     Remember
    1.34
     Depending
    1.34
     Ideally
    1.34
     Lastly
    1.33
     Also
    1.31
     Additionally
    1.30
     However
    1.28
     Beware
    1.25
    Activations Density 0.361%

    No Known Activations