© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 14563
    Prev
    Next
    INDEX
    Explanations

    words related to stun, such as "stun", "shocked", "stun gun", "stunning", etc

    oai_token-act-pair · gpt-3.5-turbo

    references to stun-related devices and their use in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eworks
    -0.75
    aternity
    -0.75
    ordan
    -0.75
    ht
    -0.71
    vernment
    -0.70
    ername
    -0.67
    yss
    -0.67
    ioch
    -0.66
    ":[
    -0.65
    ĨĴ
    -0.63
    POSITIVE LOGITS
    ingly
    1.12
    tle
    0.96
    ners
    0.94
    ted
    0.88
    ega
    0.88
    ner
    0.87
    rays
    0.86
    iflower
    0.85
    bang
    0.84
    wave
    0.84
    Activations Density 0.037%

    No Known Activations