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. 4778
    Prev
    Next
    INDEX
    Explanations

    phrases related to executive orders and political actions

    oai_token-act-pair · gpt-3.5-turbo

    references to executive orders

    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
    rown
    -0.84
     Argon
    -0.72
    dden
    -0.70
    lehem
    -0.70
    selves
    -0.66
    wo
    -0.66
     Cats
    -0.65
    yth
    -0.65
    itability
    -0.65
    iability
    -0.64
    POSITIVE LOGITS
     aimed
    0.84
     targeting
    0.83
     authorizing
    0.83
     amnesty
    0.82
     entitled
    0.79
     legalizing
    0.79
     banning
    0.79
     decree
    0.78
     issued
    0.77
     prohibiting
    0.76
    Activations Density 0.058%

    No Known Activations