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. 19830
    Prev
    Next
    INDEX
    Explanations

    phrases related to government actions, policies, and financial matters

    oai_token-act-pair · gpt-3.5-turbo

    references to government actions and policies

    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
     Tribe
    -0.79
     Semin
    -0.75
    ournals
    -0.73
     Compton
    -0.72
     ACLU
    -0.71
     Misty
    -0.70
    gyn
    -0.70
     Lauderdale
    -0.67
    cv
    -0.66
    Miami
    -0.66
    POSITIVE LOGITS
     austerity
    1.45
    usterity
    1.19
     stimulus
    1.19
     crackdown
    1.15
     privat
    1.14
     reforms
    1.12
     programmes
    1.10
     easing
    1.04
     deficit
    1.04
     clamp
    1.03
    Activations Density 0.454%

    No Known Activations