© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 23108
    Prev
    Next
    INDEX
    Explanations

    references to politicians and their positions or titles

    oai_token-act-pair · gpt-3.5-turbo

    references to government officials and their statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avored
    -0.90
     favors
    -0.88
    imize
    -0.87
     favored
    -0.86
    caliber
    -0.86
    colored
    -0.85
    zona
    -0.83
    Defense
    -0.83
     honoring
    -0.83
     favor
    -0.82
    POSITIVE LOGITS
     £
    1.54
     recognise
    1.48
     realise
    1.44
     Labour
    1.44
     centre
    1.43
     Ukip
    1.42
     Scotland
    1.41
     apologise
    1.38
    colour
    1.35
    Scotland
    1.34
    Activations Density 2.967%

    No Known Activations