© 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. 6-RES-JB
    11. 671
    Prev
    Next
    INDEX
    Explanations

    names or titles related to political leaders

    oai_token-act-pair · gpt-3.5-turbo

    references to political leaders, specifically prime ministers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lover
    -0.84
     Locations
    -0.81
    Stream
    -0.79
     Crew
    -0.74
     Campus
    -0.73
     Scene
    -0.73
    Scene
    -0.72
     Stage
    -0.72
    Limited
    -0.72
     Owners
    -0.72
    POSITIVE LOGITS
     ministers
    0.95
    onse
    0.81
     minister
    0.80
    arians
    0.79
     franc
    0.79
     ministerial
    0.77
    arian
    0.77
    thood
    0.76
    esses
    0.74
     resigned
    0.73
    Activations Density 0.058%

    No Known Activations