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. 21769
    Prev
    Next
    INDEX
    Explanations

    mentions or references to political or international relations involving the United States

    oai_token-act-pair · gpt-3.5-turbo

    references to the United States

    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
     Madden
    -0.71
     TAMADRA
    -0.70
    é¾įå
    -0.66
     McGr
    -0.66
     Mermaid
    -0.66
    osaurs
    -0.66
     Bagg
    -0.65
     shelf
    -0.65
    çīĪ
    -0.64
     Vapor
    -0.64
    POSITIVE LOGITS
    taboola
    1.00
    based
    0.99
    division
    0.96
    themed
    0.95
    backed
    0.93
    facing
    0.92
    interstitial
    0.91
    ship
    0.90
    dep
    0.88
    sized
    0.86
    Activations Density 0.014%

    No Known Activations