© 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. 3-RES-JB
    11. 673
    Prev
    Next
    INDEX
    Explanations

    mentions of governmental organizations and legal proceedings

    oai_token-act-pair · gpt-3.5-turbo

    references to government entities and public health initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    colored
    -0.90
    caliber
    -0.90
     favored
    -0.88
    avored
    -0.88
    Defense
    -0.87
    Newsletter
    -0.85
    rollment
    -0.84
     Hawai
    -0.83
    imize
    -0.83
    NBA
    -0.83
    POSITIVE LOGITS
     £
    1.44
     recognise
    1.41
     realise
    1.41
     centre
    1.34
     apologised
    1.33
     Ukip
    1.31
     scept
    1.30
     apologise
    1.30
     recognised
    1.28
     enqu
    1.27
    Activations Density 2.979%

    No Known Activations