© 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. 13211
    Prev
    Next
    INDEX
    Explanations

    words related to prisons and incarceration

    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
    920
    +0.14
    0.5%
    866
    +0.14
    0.5%
    1691
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1691
    +0.14
    0.03
    866
    +0.14
    0.03
    920
    +0.12
    0.03
    Negative Logits
     melk
    -0.51
     tages
    -0.49
     klap
    -0.47
     handels
    -0.47
    ulaski
    -0.42
    morgen
    -0.41
     knap
    -0.41
    datas
    -0.41
     herbe
    -0.41
     stille
    -0.40
    POSITIVE LOGITS
     prison
    1.12
    Prison
    1.12
    prison
    1.10
     Prison
    1.09
     prisons
    1.02
     Prisoners
    0.94
     PRISON
    0.92
     prisoners
    0.90
     Prisons
    0.88
     prisoner
    0.85
    Activations Density 0.068%

    No Known Activations