© 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. 4-RES-JB
    11. 20849
    Prev
    Next
    INDEX
    Explanations

    phrases related to turning on something or activating something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "turn on."

    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
     Annotations
    -0.82
    olds
    -0.75
    far
    -0.70
    rough
    -0.69
    Constructed
    -0.65
    mere
    -0.65
    ©¶æ¥µ
    -0.65
    perse
    -0.63
    riage
    -0.63
    enegger
    -0.62
    POSITIVE LOGITS
    shore
    0.92
     steroids
    0.79
     radar
    0.72
    wards
    0.70
     lights
    0.70
     ignition
    0.69
     autop
    0.69
    itored
    0.65
    isance
    0.63
    stage
    0.62
    Activations Density 0.038%

    No Known Activations