© 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. 1-RES-JB
    11. 16793
    Prev
    Next
    INDEX
    Explanations

    mentions of government officials, specifically ministers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political ministers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nda
    -0.72
    POS
    -0.70
    ggles
    -0.68
    ependence
    -0.65
     Kear
    -0.63
     Rouse
    -0.63
     Klu
    -0.62
    OPA
    -0.62
     Stage
    -0.61
    vae
    -0.59
    POSITIVE LOGITS
     minister
    1.21
     ministers
    1.06
     ministry
    0.92
     ministries
    0.92
    ially
    0.86
     Minister
    0.78
     Uriel
    0.77
     ministerial
    0.74
    icz
    0.73
     rabbi
    0.73
    Activations Density 0.012%

    No Known Activations