© 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
    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. 693
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and legislative actions

    oai_token-act-pair · gpt-3.5-turbo

    references to specific legislative actions or proposals

    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
    haps
    -0.77
    lier
    -0.75
     hoping
    -0.74
    agree
    -0.72
    nesday
    -0.71
     suppose
    -0.71
    ieu
    -0.70
     learnt
    -0.68
     attracts
    -0.68
     attracting
    -0.68
    POSITIVE LOGITS
     Affordable
    1.36
     nation
    1.18
     Constitution
    1.07
     Pentagon
    1.05
     ACA
    1.02
     Export
    0.98
     Keystone
    0.96
     filibuster
    0.96
     presidency
    0.95
     Voting
    0.95
    Activations Density 0.319%

    No Known Activations