© 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. 13236
    Prev
    Next
    INDEX
    Explanations

    phrases related to allegations of misconduct and controversy

    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
    198
    +0.09
    0.2%
    919
    +0.09
    0.2%
    1842
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1422
    +0.09
    0.04
    944
    +0.09
    0.03
    972
    +0.08
    0.03
    Negative Logits
     fluo
    -0.97
     thermomix
    -0.95
     ampoule
    -0.93
     oleo
    -0.81
     clayey
    -0.79
     swarovski
    -0.78
     embodi
    -0.78
     fusible
    -0.77
     pandan
    -0.75
     nutella
    -0.75
    POSITIVE LOGITS
     allegations
    0.79
     alleged
    0.67
     allegation
    0.66
     accusations
    0.66
     alleging
    0.60
     sexual
    0.59
     Muhamma
    0.57
     scandals
    0.57
     alleges
    0.56
     revelations
    0.54
    Activations Density 0.499%

    No Known Activations