© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 7835
    Prev
    Next
    INDEX
    Explanations

    mentions of social media activities and online communications

    oai_token-act-pair · gpt-3.5-turbo

    keywords and phrases related to social media and its impact on communication

    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
    thood
    -0.74
    Ö¼
    -0.72
    uxe
    -0.70
     Himself
    -0.67
    äºĶ
    -0.65
     Secondly
    -0.65
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.64
     STA
    -0.60
     Genetics
    -0.60
    jandro
    -0.59
    POSITIVE LOGITS
     congrat
    0.90
     condol
    0.87
     condolences
    0.82
     condem
    0.74
     snippets
    0.73
     pertinent
    0.69
     indicating
    0.68
    ctrl
    0.68
    ebin
    0.67
     evid
    0.67
    Activations Density 0.858%

    No Known Activations