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. 5698
    Prev
    Next
    INDEX
    Explanations

    references to the social media platform Facebook

    oai_token-act-pair · gpt-3.5-turbo

    references to Facebook in various contexts

    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
    inence
    -0.72
    ajor
    -0.70
    inav
    -0.70
    nces
    -0.69
    odied
    -0.68
     Croat
    -0.67
    arbon
    -0.67
    obin
    -0.66
    ved
    -0.66
    awk
    -0.65
    POSITIVE LOGITS
     Messenger
    1.00
    nect
    0.91
    username
    0.78
     Home
    0.72
    Ĥİ
    0.72
    icus
    0.71
     Gifts
    0.70
     Likes
    0.70
    Twitter
    0.69
     Pages
    0.69
    Activations Density 0.019%

    No Known Activations