Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 10922
    Prev
    Next
    INDEX
    Explanations

    words related to disruption or causing disturbance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "disrupt" or 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
     written
    -0.73
     Gaw
    -0.72
    owski
    -0.66
    got
    -0.66
     Purg
    -0.65
    ali
    -0.65
     sliding
    -0.63
     Written
    -0.63
    owners
    -0.62
    urance
    -0.62
    POSITIVE LOGITS
     disrupt
    3.61
     disrupting
    2.46
     disrupted
    1.95
     disruptive
    1.84
     distract
    1.49
     disruption
    1.44
     distur
    1.37
     interrupts
    1.28
     harass
    1.26
     destabil
    1.25
    Activations Density 0.018%

    No Known Activations