Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15887
    Prev
    Next
    INDEX
    Explanations

    information related to governmental activities and operations

    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
    1150
    +0.28
    0.9%
    1343
    +0.18
    0.6%
    856
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1150
    +0.28
    0.04
    856
    +0.18
    0.06
    613
    +0.15
    0.06
    Negative Logits
     swarovski
    -0.77
     tupperware
    -0.62
     ecru
    -0.62
     pandan
    -0.54
     nutella
    -0.53
     bordeaux
    -0.53
     tricot
    -0.53
     krab
    -0.52
     oleo
    -0.51
     impati
    -0.50
    POSITIVE LOGITS
     convenable
    0.66
     soigneusement
    0.62
     lentement
    0.62
     doucement
    0.60
     aussitôt
    0.58
     gynhyrchwyd
    0.55
    calciatore
    0.53
     constamment
    0.53
     librement
    0.53
     naturellement
    0.51
    Activations Density 0.732%

    No Known Activations