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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 8117
    Prev
    Next
    INDEX
    Explanations

    online petitions and related action verbs such as launched, demanding, created, campaigning, rallied, gathered, and petitioning

    oai_token-act-pair · gpt-3.5-turbo

    terms related to online petitions and activism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleasures
    -0.70
     tastes
    -0.67
     Salary
    -0.65
     senses
    -0.65
     deriv
    -0.65
     probabilities
    -0.64
     hindsight
    -0.64
    ulty
    -0.62
     flows
    -0.61
    Ö
    -0.60
    POSITIVE LOGITS
     boycott
    0.86
     advocating
    0.85
     vigil
    0.84
     hashtag
    0.82
     petition
    0.81
     protesting
    0.80
     denouncing
    0.79
     boycot
    0.79
     advocacy
    0.78
    ICE
    0.76
    Activations Density 0.397%

    No Known Activations