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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18330
    Prev
    Next
    INDEX
    Explanations

    words related to being triggered or activated in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the word "triggered" in various contexts of cause and effect

    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
    esan
    -1.06
    ians
    -0.72
     Neighbor
    -0.70
    inen
    -0.69
    enberg
    -0.68
    esa
    -0.68
     Kinnikuman
    -0.67
    ian
    -0.66
    vor
    -0.66
    ately
    -0.65
    POSITIVE LOGITS
     triggered
    1.35
     triggering
    1.25
     trigger
    1.07
     triggers
    1.05
    trigger
    0.95
    uled
    0.91
     arous
    0.89
     alarms
    0.89
     awaken
    0.86
     alarm
    0.85
    Activations Density 0.015%

    No Known Activations