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. 11-RES-JB
    6. 17851
    Prev
    Next
    INDEX
    Explanations

    social media metrics such as views, shares, and likes

    oai_token-act-pair · gpt-3.5-turbo

    metrics related to social media engagement and popularity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heter
    -0.66
    wcsstore
    -0.63
     Brav
    -0.63
     robbing
    -0.62
     transitional
    -0.61
     inexper
    -0.59
     incap
    -0.58
    dayName
    -0.58
    _-
    -0.57
     subsistence
    -0.57
    POSITIVE LOGITS
     tens
    0.97
     470
    0.93
     thousands
    0.92
    reads
    0.91
     Likes
    0.90
     367
    0.90
     279
    0.89
     260
    0.89
     259
    0.89
     Downloads
    0.88
    Activations Density 0.218%

    No Known Activations