© 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. 7411
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is find email addresses or references to a specific online platform with the word "hive"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "live."

    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
    acea
    -0.79
    erva
    -0.78
    atural
    -0.78
    committee
    -0.76
    akuya
    -0.75
    adr
    -0.72
    swick
    -0.71
    é¾įå
    -0.71
    ologically
    -0.70
    é¾
    -0.69
    POSITIVE LOGITS
    llo
    0.87
    ll
    0.77
    reth
    0.77
    rics
    0.76
    lled
    0.73
    rers
    0.71
    ttes
    0.70
    rer
    0.69
     pods
    0.69
    lli
    0.68
    Activations Density 0.016%

    No Known Activations