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. 19030
    Prev
    Next
    INDEX
    Explanations

    words related to politics and societal issues

    oai_token-act-pair · gpt-3.5-turbo

    key terms and phrases associated with political and social issues

    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
     Heads
    -0.67
    fw
    -0.66
    enegger
    -0.62
    ospels
    -0.62
    Wil
    -0.62
    redients
    -0.61
    comfort
    -0.61
    ufact
    -0.61
    Recipe
    -0.61
    ares
    -0.61
    POSITIVE LOGITS
     differ
    0.81
     arise
    0.80
     suffice
    0.75
     exist
    0.69
    adobe
    0.69
     arisen
    0.68
     shine
    0.68
    exist
    0.67
     evolve
    0.66
     emerge
    0.66
    Activations Density 0.244%

    No Known Activations