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

    Neuronpedia

    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. 6954
    Prev
    Next
    INDEX
    Explanations

    racial identifiers in a comparative context

    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
    1919
    +0.10
    0.3%
    964
    +0.09
    0.3%
    184
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1965
    +0.10
    0.04
    1919
    +0.09
    0.04
    227
    +0.09
    0.05
    Negative Logits
     mef
    -2.21
     Juf
    -2.15
     fta
    -2.08
     wien
    -1.99
     haup
    -1.94
     squa
    -1.94
     effe
    -1.94
     ftu
    -1.93
     erec
    -1.92
     Augu
    -1.92
    POSITIVE LOGITS
     has
    0.92
     was
    0.87
     is
    0.86
     likewise
    0.84
     had
    0.84
     did
    0.84
     gave
    0.83
     have
    0.82
    则
    0.81
     does
    0.81
    Activations Density 0.307%

    No Known Activations