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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 1756
    Prev
    Next
    INDEX
    Explanations

    instances where people are taking action collectively or individually

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating action or participation by people in events or activities

    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
     Advertisement
    -0.63
     Increases
    -0.60
    externalActionCode
    -0.60
     Seller
    -0.54
     Sprite
    -0.52
    berus
    -0.49
     Allows
    -0.48
    stery
    -0.48
     Lavrov
    -0.48
     Drawing
    -0.48
    POSITIVE LOGITS
    onite
    0.75
     themselves
    0.67
     theirs
    0.65
     whom
    0.62
     converge
    0.60
     interchangeable
    0.57
     respectively
    0.57
     alike
    0.56
    ebted
    0.55
     collectively
    0.55
    Activations Density 0.992%

    No Known Activations