© 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. 10-RES-JB
    11. 2228
    Prev
    Next
    INDEX
    Explanations

    phrases related to social interaction and activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of social gatherings and activities related to communal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.61
    ãĥ¤
    -0.58
    ãĤ¢ãĥ«
    -0.57
    innacle
    -0.56
    yssey
    -0.55
    å°Ĩ
    -0.55
    ãĥĥãĥĪ
    -0.54
    shown
    -0.54
    ãĥĻ
    -0.53
    ãĤ´ãĥ³
    -0.53
    POSITIVE LOGITS
     etc
    1.22
     anymore
    1.14
     whereas
    1.09
     or
    1.01
     but
    0.98
     whilst
    0.95
    ;
    0.86
     while
    0.85
     blah
    0.85
     because
    0.84
    Activations Density 0.659%

    No Known Activations