Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22841
    Prev
    Next
    INDEX
    Explanations

    words related to actions or processes happening in a specific context

    oai_token-act-pair · gpt-3.5-turbo

    terms related to processes and actions involving transition and cleanup efforts

    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
    BuyableInstoreAndOnline
    -0.59
    arij
    -0.55
     Cosponsors
    -0.53
    ãĥ¼ãĥĨãĤ£
    -0.52
     cameo
    -0.51
    Grab
    -0.50
    mber
    -0.49
    uploads
    -0.49
     Nanto
    -0.49
     typo
    -0.48
    POSITIVE LOGITS
     safely
    1.19
     efficiently
    1.15
     properly
    1.03
     correctly
    0.94
     effectively
    0.91
     worthwhile
    0.89
    .
    0.88
     reliably
    0.87
    orthy
    0.85
     securely
    0.84
    Activations Density 0.587%

    No Known Activations