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. 7-RES-JB
    6. 16627
    Prev
    Next
    INDEX
    Explanations

    words related to laws, regulations, and international treaties

    oai_token-act-pair · gpt-3.5-turbo

    key terms and phrases related to human rights and social justice issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uphill
    -0.83
     sergeant
    -0.82
     hog
    -0.79
     chuck
    -0.78
     farmer
    -0.78
    reon
    -0.78
     moon
    -0.75
    anton
    -0.74
     brim
    -0.74
     scout
    -0.74
    POSITIVE LOGITS
     Associ
    1.23
     Relations
    1.22
     Programs
    1.19
     Objects
    1.17
     Parameters
    1.15
     Activities
    1.15
     Names
    1.13
     Extensions
    1.12
     Affairs
    1.12
     Relationship
    1.10
    Activations Density 0.384%

    No Known Activations