© 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. 6863
    Prev
    Next
    INDEX
    Explanations

    words related to politics and government institutions

    oai_token-act-pair · gpt-3.5-turbo

    significant political events or discussions

    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
    _.
    -0.84
     ;)
    -0.72
    *.
    -0.71
     behav
    -0.69
    >.
    -0.69
    sic
    -0.68
    ļéĨĴ
    -0.67
    .*
    -0.67
    .;
    -0.66
    $.
    -0.65
    POSITIVE LOGITS
     Canaver
    0.63
     NASCAR
    0.62
     Hillary
    0.62
     Bernie
    0.60
     Donald
    0.57
     Pokémon
    0.55
     Hearthstone
    0.55
     POLITICO
    0.53
    uzz
    0.52
     UFC
    0.51
    Activations Density 2.795%

    No Known Activations