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. 7-RES-JB
    6. 847
    Prev
    Next
    INDEX
    Explanations

    words related to societal issues and challenges

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to urgency and the need for action in policy or healthcare contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otion
    -0.61
     lol
    -0.57
     ['
    -0.57
    esm
    -0.56
    tein
    -0.56
    lol
    -0.56
    ãĤ§
    -0.55
    bowl
    -0.55
    shoot
    -0.55
     Veget
    -0.55
    POSITIVE LOGITS
     policymakers
    1.08
     broadly
    0.77
     increasingly
    0.75
     advocates
    0.74
     politicians
    0.73
     progressives
    0.73
     urgently
    0.73
     prag
    0.70
     societal
    0.70
     broader
    0.69
    Activations Density 1.432%

    No Known Activations