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. 8389
    Prev
    Next
    INDEX
    Explanations

    phrases related to policies or actions in a political or governmental context

    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
    604
    +0.10
    0.3%
    674
    +0.07
    0.2%
    1834
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.10
    0.04
    1497
    +0.07
    0.02
    480
    +0.07
    0.03
    Negative Logits
     pama
    -0.87
     susun
    -0.87
     lyon
    -0.84
     fei
    -0.81
     levis
    -0.78
     motorola
    -0.78
     NOO
    -0.78
     jati
    -0.76
     nina
    -0.76
     lein
    -0.76
    POSITIVE LOGITS
     indirectly
    0.70
     thereby
    0.69
     implicitly
    0.68
     inadvertently
    0.59
     essentially
    0.59
     effectively
    0.57
     unwittingly
    0.56
     unknowingly
    0.55
     למע
    0.49
     basically
    0.49
    Activations Density 0.307%

    No Known Activations