© 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. 11-RES-JB
    11. 3403
    Prev
    Next
    INDEX
    Explanations

    The neuron is looking for sentences or parts of sentences that end with a period

    oai_token-act-pair · gpt-3.5-turbo

    sentences that convey conclusions or final statements

    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
     satell
    -0.97
     affili
    -0.83
     carbohyd
    -0.81
    ciplinary
    -0.77
     veter
    -0.74
     defe
    -0.74
     bios
    -0.74
     pse
    -0.73
     reluct
    -0.72
     condol
    -0.71
    POSITIVE LOGITS
     Then
    1.65
     Eventually
    1.61
     Afterwards
    1.56
     Finally
    1.53
     Lastly
    1.45
     Ultimately
    1.40
     Later
    1.34
     Once
    1.34
     Along
    1.33
     Each
    1.31
    Activations Density 0.451%

    No Known Activations