© 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. 7-RES-JB
    11. 12510
    Prev
    Next
    INDEX
    Explanations

    phrases related to behavior or conduct

    oai_token-act-pair · gpt-3.5-turbo

    references to styles or methods of behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rament
    -0.78
    hemat
    -0.71
    TOP
    -0.69
     Barton
    -0.67
    tek
    -0.66
     Neighborhood
    -0.66
     Wink
    -0.63
     STATS
    -0.63
    Dust
    -0.62
     Lyn
    -0.61
    POSITIVE LOGITS
    isms
    1.14
    othy
    0.84
    ality
    0.80
     dictated
    0.79
     ACTIONS
    0.74
    abus
    0.73
    ism
    0.69
    able
    0.68
    istic
    0.67
     consistent
    0.66
    Activations Density 0.017%

    No Known Activations