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. 8-RES-JB
    6. 18892
    Prev
    Next
    INDEX
    Explanations

    phrases indicating removal, elimination, or abolition of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the removal or elimination of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebus
    -0.78
    Pak
    -0.70
    wake
    -0.68
    Grab
    -0.65
    eous
    -0.64
    Enjoy
    -0.64
    quartered
    -0.64
    step
    -0.63
    é¾įåĸļ士
    -0.62
    format
    -0.60
    POSITIVE LOGITS
     unnecessary
    1.10
     superflu
    1.03
     altogether
    1.01
     redundant
    0.96
     pesky
    0.93
     needless
    0.92
     obsolete
    0.87
     distractions
    0.87
     any
    0.86
     unwanted
    0.79
    Activations Density 0.207%

    No Known Activations