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. 11-RES-JB
    6. 15597
    Prev
    Next
    INDEX
    Explanations

    specific legal and organizational terminology related to data protection and international transfer of data

    oai_token-act-pair · gpt-3.5-turbo

    references to international organizations and their decisions regarding protection measures

    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
     Wichita
    -0.93
    Chuck
    -0.89
     Haley
    -0.87
     Ivy
    -0.86
     Betsy
    -0.85
     phony
    -0.83
     gotten
    -0.83
    GOP
    -0.82
     folks
    -0.82
    Todd
    -0.81
    POSITIVE LOGITS
     authorised
    1.65
     derog
    1.58
     licences
    1.41
     Directive
    1.39
     recognised
    1.36
     fulfil
    1.29
     programmes
    1.28
     offences
    1.28
     envis
    1.27
     organis
    1.26
    Activations Density 0.490%

    No Known Activations