© 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. 2735
    Prev
    Next
    INDEX
    Explanations

    names of political figures and related political terms

    oai_token-act-pair · gpt-3.5-turbo

    names of political figures and references to political events

    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
    Marginal
    -0.86
    ependence
    -0.79
    livion
    -0.72
    thood
    -0.71
    DAQ
    -0.70
    oliath
    -0.69
    hett
    -0.68
    ocene
    -0.66
    eg
    -0.65
    izont
    -0.65
    POSITIVE LOGITS
     "âĢ¦
    1.01
     "'
    0.87
     "[
    0.86
     "...
    0.84
     secretly
    0.75
     "#
    0.74
     plans
    0.73
     Paddock
    0.71
     "@
    0.70
     planned
    0.70
    Activations Density 0.729%

    No Known Activations