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. 0-RES-JB
    6. 21768
    Prev
    Next
    INDEX
    Explanations

    references to legal acts or legislation

    oai_token-act-pair · gpt-3.5-turbo

    references to various legislative acts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     favorites
    -0.81
     favourites
    -0.76
     retri
    -0.70
     favorite
    -0.68
    iles
    -0.67
    rip
    -0.64
    hi
    -0.64
    gor
    -0.64
    foo
    -0.63
    jack
    -0.62
    POSITIVE LOGITS
     Act
    3.70
     Acts
    2.01
    Act
    1.98
     act
    1.84
     ACT
    1.51
     Amendment
    1.33
     Regulations
    1.29
     Legislation
    1.26
     Amendments
    1.26
     legislation
    1.16
    Activations Density 0.017%

    No Known Activations