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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 2947
    Prev
    Next
    INDEX
    Explanations

    instances of phrases indicating ensuring or verifying something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate ensuring or making sure something does not happen

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.65
     moons
    -0.64
    aughters
    -0.63
     cousins
    -0.62
     novels
    -0.62
     hobbies
    -0.59
    illon
    -0.59
    uries
    -0.58
     Reincarn
    -0.58
     ribbon
    -0.56
    POSITIVE LOGITS
     properly
    0.84
     safely
    0.82
     uninterrupted
    0.78
     adequate
    0.76
     proper
    0.74
    balanced
    0.74
     worthwhile
    0.73
    rehensive
    0.72
     appropriately
    0.70
     viable
    0.69
    Activations Density 0.256%

    No Known Activations