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. 10-RES-JB
    6. 22025
    Prev
    Next
    INDEX
    Explanations

    references to government actions and policies

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to political actions and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    tainment
    -0.78
     favourite
    -0.68
    ersive
    -0.67
     Whilst
    -0.66
     spectator
    -0.66
    emouth
    -0.64
     whilst
    -0.63
     english
    -0.62
     viewer
    -0.62
     selfie
    -0.62
    POSITIVE LOGITS
     unilaterally
    0.90
     authorizing
    0.87
     mandated
    0.87
     approving
    0.82
     bureaucratic
    0.81
     withholding
    0.76
     exemptions
    0.76
     memos
    0.75
     administr
    0.75
     exempted
    0.75
    Activations Density 1.001%

    No Known Activations