© 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. 10-RES-JB
    11. 20561
    Prev
    Next
    INDEX
    Explanations

    text related to governmental actions and policies

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to demands or recommendations in proposals

    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
    colored
    -1.15
    center
    -0.94
    caliber
    -0.93
     honor
    -0.91
     demeanor
    -0.90
    defense
    -0.90
     traveled
    -0.89
    Favorite
    -0.88
     coloring
    -0.88
    favorite
    -0.86
    POSITIVE LOGITS
     organisations
    1.58
     NHS
    1.57
     MPs
    1.53
     campaigners
    1.48
     Ministers
    1.45
     £
    1.42
     Labour
    1.38
     HM
    1.37
     councillors
    1.34
     UK
    1.33
    Activations Density 0.712%

    No Known Activations