© 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. 4-RES-JB
    6. 18496
    Prev
    Next
    INDEX
    Explanations

    references to conspiracies or criminal activities involving groups of people

    oai_token-act-pair · gpt-3.5-turbo

    references to conspiracies or plotting of illegal activities

    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
     Blizz
    -0.75
     Rockies
    -0.72
     IPA
    -0.67
     Leap
    -0.66
     Hubble
    -0.65
     Spray
    -0.65
     Sturgeon
    -0.65
    Scot
    -0.64
     Pebble
    -0.64
     pH
    -0.64
    POSITIVE LOGITS
     smuggling
    1.11
     trafficking
    1.03
     conspiring
    1.00
     paramilitary
    1.00
     plotting
    0.99
     blackmail
    0.99
     operatives
    0.98
     terrorists
    0.97
    arnaev
    0.97
     aliases
    0.97
    Activations Density 0.589%

    No Known Activations