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. 6-RES-JB
    6. 10335
    Prev
    Next
    INDEX
    Explanations

    words related to disruptions or disruptive events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to disruption and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramid
    -0.76
    eah
    -0.75
    mber
    -0.73
    rera
    -0.73
    phans
    -0.72
    uct
    -0.71
    geries
    -0.70
    uncle
    -0.69
    silver
    -0.68
    rie
    -0.68
    POSITIVE LOGITS
     disrupted
    0.96
     disruptions
    0.95
     disrupt
    0.94
    alore
    0.90
     disrupting
    0.85
     disruptive
    0.83
     disruption
    0.83
     havoc
    0.82
     interruption
    0.80
     interrupt
    0.79
    Activations Density 0.037%

    No Known Activations