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. 8186
    Prev
    Next
    INDEX
    Explanations

    actions or tasks that are challenging or difficult

    oai_token-act-pair · gpt-3.5-turbo

    verbs and phrases that indicate difficulty or ease of performing tasks

    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
    ses
    -0.69
    sis
    -0.65
    bon
    -0.61
     entitled
    -0.61
     unspecified
    -0.58
     teasp
    -0.57
    usra
    -0.56
    =~
    -0.55
    emonium
    -0.54
     Jah
    -0.53
    POSITIVE LOGITS
     oneself
    1.22
     nowadays
    1.00
     reliably
    0.90
     yourself
    0.90
     accurately
    0.88
    due
    0.86
     properly
    0.83
     correctly
    0.80
     anymore
    0.80
     efficiently
    0.79
    Activations Density 0.232%

    No Known Activations