© 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. 9-RES-JB
    11. 15716
    Prev
    Next
    INDEX
    Explanations

    politically related phrases and discussion topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legislative processes and discussions

    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
     Carnage
    -0.82
     Underworld
    -0.81
     KILL
    -0.74
     earthqu
    -0.73
     cursed
    -0.71
    Vill
    -0.71
     Shit
    -0.71
    Die
    -0.71
     ruining
    -0.71
     Fuck
    -0.71
    POSITIVE LOGITS
     briefed
    1.30
     bipartisan
    1.27
     consultations
    1.09
    Senator
    1.07
     vetted
    1.03
    displayText
    1.02
     certainly
    1.02
     briefings
    0.97
     discussions
    0.96
    ilaterally
    0.96
    Activations Density 0.905%

    No Known Activations