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. 17767
    Prev
    Next
    INDEX
    Explanations

    information related to Civil Union licenses and necessary documentation

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

    information related to legal processes and documentation requirements

    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
    CVE
    -0.85
    ãĤ¼
    -0.79
     plush
    -0.73
     downt
    -0.73
    terday
    -0.70
     slack
    -0.69
    erity
    -0.68
    ãĥķãĤ©
    -0.67
     haun
    -0.67
    ï¸ı
    -0.67
    POSITIVE LOGITS
     Fees
    1.14
     DMV
    1.08
     Registration
    1.03
     Applicant
    1.02
     Telephone
    0.99
     Forms
    0.98
     INFORMATION
    0.98
     Contact
    0.98
     mailed
    0.98
     Procedures
    0.96
    Activations Density 0.348%

    No Known Activations