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. 12-RES-JB
    6. 15098
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters and law enforcement

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    articles and references to arrests or legal actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    ngth
    -0.78
    pires
    -0.76
    ivating
    -0.64
    icious
    -0.64
    Loading
    -0.63
    avid
    -0.62
    ensions
    -0.62
    runners
    -0.62
    AMS
    -0.61
    umbered
    -0.60
    POSITIVE LOGITS
     refund
    1.06
     pardon
    1.01
     permit
    0.96
     explanation
    0.92
     continu
    0.91
     apology
    0.90
     lawyer
    0.88
     restraining
    0.88
     exemption
    0.87
     rematch
    0.87
    Activations Density 0.258%

    No Known Activations