© 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. 5076
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is find mentions of a specific name 'Me'

    oai_token-act-pair · gpt-3.5-turbo

    the first-person pronoun "Me."

    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
    pole
    -0.69
     endemic
    -0.60
     totality
    -0.59
     Cliff
    -0.59
    nings
    -0.58
     worldwide
    -0.57
     ground
    -0.57
    Closure
    -0.54
    >>\
    -0.54
    matic
    -0.52
    POSITIVE LOGITS
    asuring
    1.48
    asured
    1.32
    asures
    1.23
    zzo
    1.20
    yers
    1.17
    ghan
    1.16
    gyn
    1.15
    agher
    1.15
    asure
    1.12
    aghan
    1.09
    Activations Density 0.032%

    No Known Activations