© 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. 10-RES-JB
    11. 21771
    Prev
    Next
    INDEX
    Explanations

    references to government officials, particularly high-ranking positions like prime minister and attorney general

    oai_token-act-pair · gpt-3.5-turbo

    references to government officials and their titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pieces
    -0.81
     Participant
    -0.81
     Compos
    -0.81
     Condition
    -0.79
     Blend
    -0.75
     Locations
    -0.75
     Gate
    -0.75
    Feature
    -0.74
     Artist
    -0.74
     Latter
    -0.74
    POSITIVE LOGITS
    alty
    0.92
    ÃŃs
    0.87
     office
    0.87
    oust
    0.87
    's
    0.85
     tasked
    0.85
    ially
    0.83
     overseeing
    0.82
     himself
    0.81
     briefed
    0.78
    Activations Density 0.130%

    No Known Activations