© 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. 2681
    Prev
    Next
    INDEX
    Explanations

    topics related to political parties and historical events

    oai_token-act-pair · gpt-3.5-turbo

    topics related to political parties and their decline

    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
     referen
    -0.78
     tear
    -0.75
     sled
    -0.74
     watering
    -0.73
     rogue
    -0.73
     standby
    -0.71
    etsk
    -0.71
     logger
    -0.70
     sunshine
    -0.68
    mble
    -0.68
    POSITIVE LOGITS
    ?,
    1.22
     Strategies
    1.01
     Syndrome
    0.98
     Written
    0.96
     Volume
    0.96
     Culture
    0.94
     Terrorism
    0.93
     (?,
    0.92
    _.
    0.91
     Patterns
    0.88
    Activations Density 0.298%

    No Known Activations