© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5518
    Prev
    Next
    INDEX
    Explanations

    words related to control and authority

    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
    404
    +0.11
    0.4%
    25
    +0.11
    0.4%
    161
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.11
    0.04
    492
    +0.11
    0.04
    795
    +0.10
    0.02
    Negative Logits
     indestru
    -0.89
     disgra
    -0.83
     Abbé
    -0.79
     unlaw
    -0.76
     naï
    -0.75
     revan
    -0.75
     embra
    -0.74
     impractica
    -0.74
     pessi
    -0.74
     dilap
    -0.74
    POSITIVE LOGITS
     control
    1.54
    control
    1.44
     Control
    1.41
     CONTROL
    1.32
    Control
    1.31
     controls
    1.29
    CONTROL
    1.24
    controls
    1.16
     Controls
    1.16
    controlled
    1.14
    Activations Density 0.104%

    No Known Activations