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. 4-RES-JB
    6. 14977
    Prev
    Next
    INDEX
    Explanations

    donations or offers mentioned in tweets

    oai_token-act-pair · gpt-3.5-turbo

    references to online interactions and social media comments

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

    No Comments

    Negative Logits
     Agric
    -0.82
     apprentices
    -0.74
    dependent
    -0.73
    aceae
    -0.71
    .ãĢį
    -0.69
     mould
    -0.67
     sustainable
    -0.67
     subsistence
    -0.66
     ageing
    -0.66
     export
    -0.65
    POSITIVE LOGITS
     retweet
    1.41
     tweets
    1.19
     tweeted
    1.11
     hasht
    1.08
     TMZ
    1.07
     tweeting
    1.03
     tweet
    1.03
    weet
    0.96
     Twitter
    0.96
     BuzzFeed
    0.94
    Activations Density 1.435%

    No Known Activations