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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 12707
    Prev
    Next
    INDEX
    Explanations

    terms related to political revolutions and coups

    oai_token-act-pair · gpt-3.5-turbo

    instances of political overthrow or regime change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dragonbound
    -0.85
    Scot
    -0.81
     Gat
    -0.74
    except
    -0.74
    Gas
    -0.74
    Room
    -0.72
    Reader
    -0.72
    Interest
    -0.72
    Hop
    -0.72
    Act
    -0.71
    POSITIVE LOGITS
     overth
    1.61
     overthrow
    1.53
     topple
    1.22
     toppled
    1.17
     ousted
    1.07
     topp
    0.98
     dictator
    0.89
     dictatorship
    0.89
     democratically
    0.88
     dictators
    0.85
    Activations Density 0.017%

    No Known Activations