© 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 · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 7675
    Prev
    Next
    INDEX
    Explanations

    phrases related to surveillance and monitoring

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    946
    +0.09
    0.3%
    266
    +0.09
    0.3%
    188
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.09
    0.04
    266
    +0.09
    0.04
    1962
    +0.09
    0.04
    Negative Logits
     suscep
    -1.02
     impra
    -0.97
     affor
    -0.95
     erad
    -0.94
     increa
    -0.94
     reluct
    -0.91
     effe
    -0.91
     unden
    -0.90
     compen
    -0.88
     volunte
    -0.87
    POSITIVE LOGITS
     monitor
    0.93
     monitoring
    0.93
     monitored
    0.83
     closely
    0.82
     monitors
    0.81
     tracking
    0.81
    monitoring
    0.80
    monitor
    0.77
     Monitoring
    0.76
     Monitor
    0.73
    Activations Density 0.329%

    No Known Activations