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. 10-RES-JB
    6. 2436
    Prev
    Next
    INDEX
    Explanations

    words related to legal matters such as lawyers, lawsuits, and legal actions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CRE
    -0.73
    tml
    -0.71
    ãĥ¬
    -0.69
    使
    -0.68
     unreal
    -0.67
    ¥µ
    -0.65
    ãĤ¡
    -0.64
    heast
    -0.63
    / 
    -0.62
    erial
    -0.62
    POSITIVE LOGITS
     denies
    1.22
     apologized
    1.20
     himself
    1.14
     reportedly
    1.14
     denied
    1.12
     supporters
    1.09
     spokesman
    1.07
     declined
    1.07
     testified
    1.06
     thanked
    1.02
    Activations Density 0.262%

    No Known Activations