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. 10-RES-JB
    6. 19227
    Prev
    Next
    INDEX
    Explanations

    criteria or conditions that need to be met

    oai_token-act-pair · gpt-3.5-turbo

    phrases pertaining to safety, requirements, and rules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interstitial
    -0.79
    olor
    -0.71
    bye
    -0.68
     handwriting
    -0.66
     Doodle
    -0.65
    Posts
    -0.64
     slideshow
    -0.64
    ividual
    -0.63
     DRAG
    -0.61
     hail
    -0.60
    POSITIVE LOGITS
     fulfilled
    1.04
     omitted
    1.03
     utilized
    1.03
     preserved
    1.03
     emphasized
    1.01
     minimized
    1.00
     violated
    0.99
     consulted
    0.99
     exceeded
    0.98
     explored
    0.97
    Activations Density 0.235%

    No Known Activations