© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 20671
    Prev
    Next
    INDEX
    Explanations

    terms related to territorial disputes or claims

    oai_token-act-pair · gpt-3.5-turbo

    references to territorial and maritime claims or boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ggies
    -0.85
    OHN
    -0.82
    ources
    -0.80
    udder
    -0.79
    ovie
    -0.78
    OPLE
    -0.77
    $$
    -0.77
    Episode
    -0.77
    ppel
    -0.76
    erer
    -0.76
    POSITIVE LOGITS
     sovere
    1.07
     boundaries
    0.96
     territorial
    0.95
     sovereignty
    0.94
     warr
    0.84
     disputes
    0.82
     defence
    0.80
     territ
    0.80
     warfare
    0.80
     citiz
    0.79
    Activations Density 0.006%

    No Known Activations