Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15946
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    references to legal rights and recognitions for marginalized groups

    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
    \/\/
    -0.77
    ngth
    -0.73
     Niet
    -0.72
    rust
    -0.71
     Guys
    -0.71
     Fail
    -0.70
     sqor
    -0.69
    bub
    -0.68
    meta
    -0.68
     Brands
    -0.66
    POSITIVE LOGITS
     immunity
    1.24
     citizenship
    1.23
     protection
    1.19
     asylum
    1.18
     protections
    1.14
     amnesty
    1.12
     residency
    1.11
     visas
    1.11
     visitation
    1.09
     anonymity
    1.08
    Activations Density 0.211%

    No Known Activations