© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 17779
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is find words related to advertisements or promotions

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the abbreviation "Ad" in various contexts

    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
     Kubrick
    -0.69
    Jr
    -0.68
     trout
    -0.68
     Stronghold
    -0.67
     Weir
    -0.66
     crab
    -0.63
     biomass
    -0.61
     wool
    -0.61
     Tsukuyomi
    -0.60
     Bulg
    -0.60
    POSITIVE LOGITS
    vertis
    1.41
    mittedly
    1.33
    olescent
    1.31
    elaide
    1.28
    vance
    1.24
    vantage
    1.23
    olesc
    1.21
    vertising
    1.21
    ventures
    1.20
    ept
    1.20
    Activations Density 0.027%

    No Known Activations