© 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. 5683
    Prev
    Next
    INDEX
    Explanations

    references to slavery and related historical events and issues

    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
    1124
    +0.14
    0.5%
    1964
    +0.11
    0.4%
    1961
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1124
    +0.14
    0.02
    976
    +0.11
    0.02
    130
    +0.11
    0.02
    Negative Logits
     كومونز
    -0.53
     munt
    -0.50
     autorytatywna
    -0.49
    upsi
    -0.48
     originalen
    -0.47
     peliculas
    -0.45
    ceptre
    -0.45
    ennheiser
    -0.45
     MaterialApp
    -0.45
    featureID
    -0.45
    POSITIVE LOGITS
     slave
    1.22
    Slave
    1.18
     slaves
    1.16
    slave
    1.14
     Slaves
    1.14
     Slave
    1.13
     slavery
    1.10
     Slavery
    1.10
     ensla
    0.94
    Sla
    0.91
    Activations Density 0.098%

    No Known Activations