© 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. 2-RES-JB
    11. 8949
    Prev
    Next
    INDEX
    Explanations

    words related to alerts or warnings

    oai_token-act-pair · gpt-3.5-turbo

    various contexts in which the term "alert" is used

    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
    76561
    -0.70
    apers
    -0.69
    dx
    -0.69
    ANN
    -0.65
    Plex
    -0.64
    PE
    -0.64
    anne
    -0.64
    Untitled
    -0.64
    BLE
    -0.62
    xp
    -0.62
    POSITIVE LOGITS
     alert
    1.17
    ingly
    0.99
     alerts
    0.98
     Alert
    0.95
    ness
    0.90
    alert
    0.86
    Alert
    0.82
     alerted
    0.80
    ibility
    0.79
    gency
    0.76
    Activations Density 0.014%

    No Known Activations