© 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. 4-RES-JB
    11. 3233
    Prev
    Next
    INDEX
    Explanations

    terms related to political organizations, specifically references to the DNC (Democratic National Committee)

    oai_token-act-pair · gpt-3.5-turbo

    references to the Democratic National Committee (DNC)

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

    No Comments

    Negative Logits
     Kubrick
    -0.75
    otropic
    -0.71
    ggies
    -0.68
     Kafka
    -0.68
    rily
    -0.68
     Britann
    -0.67
     Shinji
    -0.67
    ãĤ¹ãĥĪ
    -0.67
    perm
    -0.66
    gered
    -0.66
    POSITIVE LOGITS
    agogue
    0.87
     DNC
    0.86
     chair
    0.85
     Chair
    0.83
    ilion
    0.82
    Leaks
    0.82
     treasury
    0.80
    olicy
    0.78
     staffer
    0.77
    CCC
    0.75
    Activations Density 0.016%

    No Known Activations