© 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. 11-RES-JB
    11. 7505
    Prev
    Next
    INDEX
    Explanations

    elements related to a sense of connection and belonging within a group or community

    oai_token-act-pair · gpt-3.5-turbo

    themes related to community and shared experiences

    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
     confir
    -0.74
    nesday
    -0.56
     sugg
    -0.54
     namely
    -0.53
    ãĥį
    -0.52
     streng
    -0.51
    ËĪ
    -0.50
    prisingly
    -0.50
    named
    -0.49
     predecessor
    -0.49
    POSITIVE LOGITS
     etc
    1.18
    âĢ¦"
    1.04
    âĢ¦
    1.04
    ,...
    1.01
    âĢ¦)
    0.98
    ,
    0.98
     âĢ¦"
    0.94
     âĢ¦
    0.92
    âĢ¦.
    0.91
    ,—
    0.90
    Activations Density 0.280%

    No Known Activations