© 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. 8-RES-JB
    11. 2054
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussions and meetings on political and policy matters

    oai_token-act-pair · gpt-3.5-turbo

    topics related to discussions and meetings about political and social issues

    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
     Inquis
    -0.70
    ucket
    -0.70
    ario
    -0.68
    âĺĨ
    -0.67
     fooled
    -0.66
    ographers
    -0.66
     thief
    -0.65
    Torrent
    -0.64
    ItemImage
    -0.64
     Stores
    -0.62
    POSITIVE LOGITS
     topics
    1.10
     matters
    0.94
     feasibility
    0.91
     issues
    0.88
     behalf
    0.84
     ethics
    0.83
     impeachment
    0.82
     grievances
    0.82
     ideas
    0.80
     particulars
    0.79
    Activations Density 0.267%

    No Known Activations