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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 20566
    Prev
    Next
    INDEX
    Explanations

    the word "let" followed by a number indicating urgency or priority

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "let" followed by numerical values indicating commands or suggestions

    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
     holiest
    -0.74
     Soldier
    -0.64
    Zen
    -0.63
    atana
    -0.62
    PLIED
    -0.61
    manship
    -0.61
    oppable
    -0.59
     cumbers
    -0.59
    AGES
    -0.58
     vending
    -0.57
    POSITIVE LOGITS
    tered
    1.00
    tering
    0.91
    icia
    0.82
    itia
    0.82
    ting
    0.80
     us
    0.75
    TB
    0.66
    winter
    0.66
    cheon
    0.65
    enne
    0.65
    Activations Density 0.027%

    No Known Activations