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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 3534
    Prev
    Next
    INDEX
    Explanations

    mentions of uniforms and uniformed personnel

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "uniform" and its variations

    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
    UD
    -0.82
    heimer
    -0.78
    ×Ļ×
    -0.75
    borough
    -0.73
    doors
    -0.72
    ofi
    -0.71
    AMY
    -0.70
    udic
    -0.70
     å¤
    -0.68
    than
    -0.68
    POSITIVE LOGITS
     uniforms
    1.05
    ity
    1.01
     worn
    0.94
    itarian
    0.93
     bearer
    0.90
    iating
    0.88
     uniform
    0.87
     insign
    0.87
     attire
    0.82
     apparel
    0.81
    Activations Density 0.018%

    No Known Activations