© 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. 9-RES-JB
    6. 8612
    Prev
    Next
    INDEX
    Explanations

    statements related to political systems and ideologies

    oai_token-act-pair · gpt-3.5-turbo

    ideas about societal structures and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cuff
    -0.86
     actionGroup
    -0.80
     annoyance
    -0.78
     filings
    -0.71
    damage
    -0.71
     irritation
    -0.70
    ãĤĵ
    -0.70
     clearance
    -0.70
     spike
    -0.69
     citations
    -0.68
    POSITIVE LOGITS
     envisioned
    1.16
     Socialism
    1.08
     dystop
    1.07
     envis
    1.04
     utopian
    1.03
     paradise
    0.99
     dystopian
    0.99
    topia
    0.94
     Capitalism
    0.94
     socialism
    0.93
    Activations Density 0.749%

    No Known Activations