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. 15882
    Prev
    Next
    INDEX
    Explanations

    mentions of marches and protests in political contexts

    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
    1604
    +0.12
    0.4%
    25
    +0.11
    0.4%
    1480
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1604
    +0.12
    0.02
    1565
    +0.11
    0.02
    1520
    +0.10
    0.02
    Negative Logits
     nonatomic
    -0.59
     Ufer
    -0.57
     Preferencias
    -0.57
    يكب
    -0.53
    testify
    -0.52
     kaynağından
    -0.52
    YECTO
    -0.50
     relâche
    -0.50
     minuta
    -0.49
     Paglinawan
    -0.49
    POSITIVE LOGITS
     march
    1.44
     marches
    1.36
     marched
    1.31
     marching
    1.25
     unspeak
    1.23
     apprehen
    1.17
     disagre
    1.15
     gaily
    1.13
     unwarran
    1.10
     indestru
    1.10
    Activations Density 0.060%

    No Known Activations