© 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. 0-RES-JB
    11. 6724
    Prev
    Next
    INDEX
    Explanations

    instances of triggering or being triggered

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "triggered" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     excellence
    -0.86
    maxwell
    -0.67
    cellence
    -0.66
    bern
    -0.65
    oft
    -0.65
    inis
    -0.63
    RIC
    -0.62
     brill
    -0.62
     liv
    -0.60
     Comparison
    -0.60
    POSITIVE LOGITS
     triggered
    3.58
     triggering
    2.26
     triggers
    2.03
     trigger
    1.86
     activated
    1.75
     provoked
    1.65
    trigger
    1.55
     invoked
    1.47
    Trigger
    1.42
     Trigger
    1.40
    Activations Density 0.023%

    No Known Activations