© 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. 0-RES-JB
    11. 4069
    Prev
    Next
    INDEX
    Explanations

    terms related to political topics

    oai_token-act-pair · gpt-3.5-turbo

    references to political themes or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sight
    -0.72
     hook
    -0.71
     starter
    -0.71
     champ
    -0.71
     blink
    -0.70
     blaze
    -0.70
     flush
    -0.69
    ooo
    -0.67
     kits
    -0.66
     shut
    -0.66
    POSITIVE LOGITS
     Political
    3.45
    Political
    2.42
     Politics
    1.82
     Polit
    1.72
     POLIT
    1.70
    Politics
    1.69
    political
    1.63
    Polit
    1.52
     Elections
    1.49
     Voter
    1.46
    Activations Density 0.024%

    No Known Activations