© 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. 0-RES-JB
    11. 5275
    Prev
    Next
    INDEX
    Explanations

    social-related terms or phrases

    oai_token-act-pair · gpt-3.5-turbo

    mentions of social media and its impact or involvement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rings
    -0.78
     Malf
    -0.75
    assembled
    -0.72
     Bullets
    -0.72
    zen
    -0.70
     Array
    -0.70
    ridge
    -0.69
     apiece
    -0.68
    pler
    -0.68
    arry
    -0.68
    POSITIVE LOGITS
     social
    3.37
    social
    2.54
    Social
    2.52
     Social
    2.33
     socially
    2.10
     socio
    1.80
     soc
    1.77
     societal
    1.77
    ocial
    1.73
     socioeconomic
    1.69
    Activations Density 0.031%

    No Known Activations