© 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. 7-RES-JB
    11. 7220
    Prev
    Next
    INDEX
    Explanations

    political terms and affiliations, particularly related to the United States

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OST
    -0.82
    osc
    -0.75
    Fish
    -0.75
    oscope
    -0.74
    Premium
    -0.70
    chart
    -0.66
    ost
    -0.66
     Spa
    -0.66
    join
    -0.66
    ometimes
    -0.65
    POSITIVE LOGITS
     sentiment
    1.08
     sentiments
    1.01
     crus
    0.89
     rhetoric
    0.87
     hysteria
    0.84
     demonstrators
    0.84
     stance
    0.81
     slogans
    0.81
     demonstrations
    0.80
     coalition
    0.80
    Activations Density 0.074%

    No Known Activations