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. 0-RES-JB
    6. 21300
    Prev
    Next
    INDEX
    Explanations

    sentences containing the word "problem."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the concept of a "problem."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ounces
    -0.79
    é¾įåĸļ士
    -0.74
    Scotland
    -0.73
    thouse
    -0.68
    nces
    -0.68
    asts
    -0.68
     Vide
    -0.66
     Tours
    -0.65
    ofi
    -0.65
    ributes
    -0.64
    POSITIVE LOGITS
     problem
    3.45
    problem
    2.81
     Problem
    2.74
    Problem
    2.38
     problems
    2.19
     issue
    1.97
     Problems
    1.82
     dilemma
    1.81
     trouble
    1.67
     proble
    1.66
    Activations Density 0.027%

    No Known Activations