© 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. 2-RES-JB
    11. 23751
    Prev
    Next
    INDEX
    Explanations

    instances where someone is being contacted for various reasons

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "contacted."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fruit
    -0.78
    oil
    -0.77
    cakes
    -0.73
    whatever
    -0.73
    pite
    -0.72
    fast
    -0.72
    reci
    -0.71
    serving
    -0.71
    few
    -0.70
    cake
    -0.70
    POSITIVE LOGITS
     contacted
    0.93
    ertodd
    0.77
    ashtra
    0.74
     Leica
    0.73
     beforehand
    0.72
    izabeth
    0.72
    lehem
    0.71
     Vick
    0.68
     interviews
    0.67
     contacts
    0.67
    Activations Density 0.026%

    No Known Activations