© 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. 2-RES-JB
    11. 19613
    Prev
    Next
    INDEX
    Explanations

    words related to alarms and alerts

    oai_token-act-pair · gpt-3.5-turbo

    the concept of "alarm" in various contexts

    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
    lease
    -0.76
    tein
    -0.74
    Untitled
    -0.72
    hire
    -0.71
    atted
    -0.69
    cca
    -0.68
    teen
    -0.68
    frey
    -0.65
    arnaev
    -0.65
    buff
    -0.65
    POSITIVE LOGITS
     alarm
    1.11
     alarms
    1.06
     bells
    1.05
    ingly
    0.97
     Clock
    0.96
     clock
    0.94
    clock
    0.91
    Clock
    0.86
     clocks
    0.86
    ously
    0.74
    Activations Density 0.010%

    No Known Activations