© 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 EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 12642
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is find sentences that end with specific formatting characters

    oai_token-act-pair · gpt-3.5-turbo

    the presence of high-stakes scenarios or critical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     withdraw
    -0.72
    iton
    -0.67
    heit
    -0.67
    pan
    -0.66
     manoeuv
    -0.65
     Cent
    -0.65
     Creed
    -0.65
     upstairs
    -0.60
    wolves
    -0.59
     intending
    -0.59
    POSITIVE LOGITS
    ³³³
    0.97
    ³³³³
    0.89
    Consider
    0.86
    ³³³³³³³³
    0.81
    Fans
    0.81
    ³³³³³³³³³³³³³³³³
    0.79
    ccording
    0.78
    SEE
    0.77
    ³³
    0.74
    Specifically
    0.72
    Activations Density 0.414%

    No Known Activations