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. 11-RES-JB
    6. 3938
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal and constitutional matters

    oai_token-act-pair · gpt-3.5-turbo

    references to legal rights and constitutional provisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ritz
    -0.71
     srfAttach
    -0.69
    iddling
    -0.67
    bite
    -0.66
     Decay
    -0.65
     palate
    -0.65
     è£ıè
    -0.63
    Pie
    -0.62
    Experience
    -0.62
    dden
    -0.62
    POSITIVE LOGITS
     prohibits
    1.68
     forbids
    1.66
     specifies
    1.51
     stip
    1.43
     states
    1.40
     regulates
    1.36
     mandates
    1.34
     presc
    1.33
     governs
    1.31
     permits
    1.31
    Activations Density 0.307%

    No Known Activations