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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-RES-JB
    6. 5741
    Prev
    Next
    INDEX
    Explanations

    references to social media platforms, especially Facebook

    oai_token-act-pair · gpt-3.5-turbo

    mentions and references to the social media platform Facebook

    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
    nces
    -0.87
    ved
    -0.73
    lass
    -0.69
    ptin
    -0.68
    DERR
    -0.68
     externalToEVAOnly
    -0.67
    rer
    -0.67
    dry
    -0.67
    heny
    -0.67
    teen
    -0.66
    POSITIVE LOGITS
     Messenger
    0.97
    nect
    0.94
     Live
    0.84
    acebook
    0.78
    icus
    0.77
     Pages
    0.76
    ical
    0.76
    imity
    0.76
    username
    0.76
     Caf
    0.72
    Activations Density 0.040%

    No Known Activations