© 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. 6888
    Prev
    Next
    INDEX
    Explanations

    phrases related to business or political campaigns

    oai_token-act-pair · gpt-3.5-turbo

    references to campaigns and 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
     oneself
    -0.84
     ourselves
    -0.77
    aples
    -0.74
     GOODMAN
    -0.66
    urers
    -0.66
     Feder
    -0.64
    ickson
    -0.61
    pires
    -0.61
    Ĥª
    -0.61
     Kejriwal
    -0.60
    POSITIVE LOGITS
     autobiography
    0.84
     antics
    0.78
     persona
    0.75
     woes
    0.69
     spree
    0.69
     masterpiece
    0.68
     career
    0.68
     theorem
    0.67
     biography
    0.66
     tenure
    0.66
    Activations Density 0.558%

    No Known Activations