© 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. 4-RES-JB
    11. 17337
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is find names or references to the individual "Reynolds."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities, particularly "Reynolds" and related terms

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

    No Comments

    Negative Logits
    ulhu
    -0.82
    »Ĵ
    -0.74
    Bloom
    -0.67
     respectively
    -0.65
    çĶŁ
    -0.65
    acca
    -0.63
    inventoryQuantity
    -0.62
    lehem
    -0.60
    catentry
    -0.60
    ARI
    -0.60
    POSITIVE LOGITS
    issance
    1.10
    itory
    0.85
    ndum
    0.81
    enegger
    0.80
    ption
    0.77
    earch
    0.76
    xual
    0.75
    irmation
    0.73
    kefeller
    0.73
    rocal
    0.72
    Activations Density 0.106%

    No Known Activations