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. 10-RES-JB
    6. 53
    Prev
    Next
    INDEX
    Explanations

    terms related to monitoring and surveillance

    oai_token-act-pair · gpt-3.5-turbo

    commands or discussions related to oversight and observation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ̶
    -0.83
    uti
    -0.79
    erella
    -0.75
    Myth
    -0.74
    ©¶æ¥µ
    -0.73
    arak
    -0.73
    vable
    -0.73
    hire
    -0.71
    ãĥ´
    -0.71
    adr
    -0.70
    POSITIVE LOGITS
     developments
    1.33
     closely
    1.19
     movements
    0.90
     trends
    0.86
     monitors
    0.85
     progress
    0.84
     compliance
    0.83
     attent
    0.82
     fluctuations
    0.81
     monitoring
    0.80
    Activations Density 0.068%

    No Known Activations