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. 2-RES-JB
    6. 20272
    Prev
    Next
    INDEX
    Explanations

    instances of the word "panic"

    oai_token-act-pair · gpt-3.5-turbo

    references to feelings of panic or anxiety

    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
    ĻĤ
    -1.01
    Ģ
    -0.77
    çĦ
    -0.76
    detail
    -0.75
    posted
    -0.74
    ľ
    -0.71
    friend
    -0.71
    tein
    -0.70
    optional
    -0.69
    teen
    -0.69
    POSITIVE LOGITS
     panic
    1.03
     hyster
    0.94
     Panic
    0.86
     paralysis
    0.82
     pandemonium
    0.78
     hysteria
    0.76
    ulence
    0.74
    iness
    0.73
     earthqu
    0.72
     uproar
    0.71
    Activations Density 0.006%

    No Known Activations