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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 22447
    Prev
    Next
    INDEX
    Explanations

    organizations and groups related to political activism

    oai_token-act-pair · gpt-3.5-turbo

    references to political organizations and committees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     puzz
    -0.76
     simulator
    -0.75
     clay
    -0.74
     circumst
    -0.72
     whim
    -0.72
     blender
    -0.71
     blush
    -0.71
     fancy
    -0.71
     departments
    -0.70
     rumours
    -0.69
    POSITIVE LOGITS
     Coalition
    1.07
     Voters
    1.04
     Initiative
    1.03
     Democracy
    0.99
    Choice
    0.96
     Vote
    0.96
     Agenda
    0.96
    Vote
    0.93
     Progress
    0.92
     Equality
    0.92
    Activations Density 0.314%

    No Known Activations