© 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. 17217
    Prev
    Next
    INDEX
    Explanations

    words related to criminal activities, specifically stalking and theft

    oai_token-act-pair · gpt-3.5-turbo

    terms related to stalking and valuable items, particularly jewels

    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
    resso
    -0.91
    poon
    -0.89
    lated
    -0.82
    poons
    -0.80
    zik
    -0.80
    rites
    -0.79
    endum
    -0.79
    omsky
    -0.79
    ixed
    -0.79
    enei
    -0.77
    POSITIVE LOGITS
     stalk
    0.94
     stalking
    0.88
    lihood
    0.78
    hunt
    0.76
    ////////////////
    0.73
    gow
    0.72
    Tro
    0.70
    Upload
    0.69
     Fenrir
    0.69
    Cra
    0.69
    Activations Density 0.016%

    No Known Activations