© 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. 1-RES-JB
    11. 19998
    Prev
    Next
    INDEX
    Explanations

    words related to militarization and pacifism

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to militarization and its consequences

    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
    Recommend
    -0.82
    article
    -0.73
    lihood
    -0.72
    Gi
    -0.71
     Nile
    -0.70
    Distance
    -0.69
    License
    -0.68
    Title
    -0.68
    Article
    -0.68
    Mary
    -0.67
    POSITIVE LOGITS
     militar
    1.37
    ilitary
    1.05
    hement
    0.93
    ische
    0.88
     indo
    0.87
    iazep
    0.87
    ificent
    0.85
    riors
    0.85
     mascul
    0.85
    istic
    0.85
    Activations Density 0.011%

    No Known Activations