© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 1681
    Prev
    Next
    INDEX
    Explanations

    mentions of scientific bodies or experts

    oai_token-act-pair · gpt-3.5-turbo

    references to scientists and officials in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     assistant
    -0.84
     fate
    -0.83
     critic
    -0.82
     pale
    -0.81
     director
    -0.80
     net
    -0.78
     integration
    -0.76
     interests
    -0.76
     appropri
    -0.75
     ass
    -0.75
    POSITIVE LOGITS
     Scientists
    2.07
     Officials
    1.95
     Voters
    1.90
     Researchers
    1.84
     Prosecutors
    1.77
     Authorities
    1.77
     Experts
    1.74
     Investigators
    1.65
     Supporters
    1.62
     Visitors
    1.59
    Activations Density 0.085%

    No Known Activations