© 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. 6505
    Prev
    Next
    INDEX
    Explanations

    texts related to political and government actions or reform

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to governmental action and reform

    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
    paio
    -0.64
     mysteriously
    -0.61
     Fancy
    -0.61
     Paddock
    -0.60
     unlucky
    -0.59
    Flight
    -0.59
     Wedding
    -0.59
     fame
    -0.59
    >[
    -0.58
    lua
    -0.57
    POSITIVE LOGITS
     urgently
    1.03
     policymakers
    0.95
     equitable
    0.95
     legisl
    0.93
     reforms
    0.90
     accountability
    0.88
     responsibly
    0.88
     accountable
    0.87
     educate
    0.86
     proactive
    0.86
    Activations Density 1.089%

    No Known Activations