© 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. 0-RES-JB
    11. 4104
    Prev
    Next
    INDEX
    Explanations

    the name "Navalny" as it appears in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Naval."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urus
    -0.80
    aways
    -0.72
    osity
    -0.71
     Karma
    -0.69
    walker
    -0.68
     buck
    -0.66
    writer
    -0.66
    ggies
    -0.65
    abbit
    -0.63
    ogie
    -0.62
    POSITIVE LOGITS
     Naval
    3.03
     naval
    2.99
     maritime
    1.51
     warships
    1.37
     navy
    1.21
     Maritime
    1.19
     submar
    1.18
     military
    1.18
     submarine
    1.14
     NAV
    1.14
    Activations Density 0.011%

    No Known Activations