© 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. 2-RES-JB
    6. 21010
    Prev
    Next
    INDEX
    Explanations

    terms related to the cybersecurity incident known as WannaCry

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Anna."

    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
    matically
    -0.83
     skelet
    -0.77
    nces
    -0.75
    rid
    -0.75
    tick
    -0.74
    Assembly
    -0.73
    ticket
    -0.72
    dem
    -0.72
    tle
    -0.72
    lasses
    -0.72
    POSITIVE LOGITS
    anna
    0.98
    isance
    0.90
     Mae
    0.89
     Marie
    0.77
    uthor
    0.76
    ð
    0.73
    utical
    0.70
    jit
    0.69
     Grande
    0.69
     Borough
    0.67
    Activations Density 0.009%

    No Known Activations