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

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 17880
    Prev
    Next
    INDEX
    Explanations

    mentions of phone calls, especially those discussing requests or complaints

    oai_token-act-pair · gpt-3.5-turbo

    instances of communication or requests being made

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ema
    -0.68
     presidency
    -0.67
     predecessor
    -0.67
     Compass
    -0.66
    onom
    -0.65
     Means
    -0.61
     Govern
    -0.61
     successor
    -0.61
     lender
    -0.60
    ursion
    -0.60
    POSITIVE LOGITS
     frantically
    0.93
     piles
    0.92
     endlessly
    0.89
     dinners
    0.88
     snippets
    0.86
    iddles
    0.84
     tons
    0.84
     pots
    0.83
     stuff
    0.83
     rows
    0.82
    Activations Density 0.973%

    No Known Activations