Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 21692
    Prev
    Next
    INDEX
    Explanations

    legal and political terms related to international agreements and laws

    oai_token-act-pair · gpt-3.5-turbo

    legal and political terminology related to formal agreements and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Milwaukee
    -0.75
     Fresno
    -0.70
     Wisconsin
    -0.69
     Packers
    -0.69
    Wisconsin
    -0.69
     Seattle
    -0.68
     Pittsburgh
    -0.66
    Colorado
    -0.66
     Prescott
    -0.65
    Veter
    -0.64
    POSITIVE LOGITS
    bourg
    0.88
     decre
    0.84
     envis
    0.84
     decree
    0.82
     authorised
    0.77
     favourable
    0.77
     UNESCO
    0.76
    20439
    0.75
     enacted
    0.75
     unanimously
    0.74
    Activations Density 0.177%

    No Known Activations