© 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. 7245
    Prev
    Next
    INDEX
    Explanations

    content related to political and environmental 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
    674
    +0.09
    0.2%
    2034
    +0.07
    0.2%
    872
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.09
    0.04
    1318
    +0.07
    0.04
    1455
    +0.07
    0.04
    Negative Logits
     emphat
    -1.26
     depic
    -1.22
     maneu
    -1.22
     increa
    -1.16
     indestru
    -1.14
     encomp
    -1.14
     resear
    -1.13
     feen
    -1.13
     volunte
    -1.12
     disagre
    -1.11
    POSITIVE LOGITS
     ***!
    0.91
     nor
    0.76
     sondern
    0.76
     Nope
    0.69
    而是
    0.69
    
    0.67
    nor
    0.67
    SafeAreaView
    0.66
     hanem
    0.66
    Nope
    0.61
    Activations Density 0.234%

    No Known Activations