© 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 EvalsExportsinterp-engineNEWAPI 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. 4852
    Prev
    Next
    INDEX
    Explanations

    instances of violent and hate speech

    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
    674
    +0.12
    0.3%
    1842
    +0.10
    0.3%
    394
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.12
    0.07
    1261
    +0.10
    0.02
    946
    +0.10
    0.05
    Negative Logits
     antik
    -0.79
     maksi
    -0.73
     praktik
    -0.69
     makro
    -0.69
     conster
    -0.64
     minimalis
    -0.64
     ché
    -0.62
     keramik
    -0.61
     optik
    -0.61
     abstrak
    -0.60
    POSITIVE LOGITS
     kill
    0.61
     killing
    0.60
     killed
    0.59
     Killed
    0.53
     kills
    0.52
     deaths
    0.52
    kill
    0.52
    ⓧ
    0.49
     murdering
    0.49
     apoptotic
    0.49
    Activations Density 0.640%

    No Known Activations