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. 15513
    Prev
    Next
    INDEX
    Explanations

    references to social, political, and economic issues, particularly related to government policies and activities

    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
    227
    +0.11
    0.3%
    478
    +0.10
    0.3%
    764
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.11
    0.06
    1348
    +0.10
    0.04
    478
    +0.08
    0.04
    Negative Logits
     remonte
    -0.63
     moza
    -0.59
     palet
    -0.58
     jawa
    -0.58
     clientèle
    -0.58
     karna
    -0.58
     koch
    -0.56
     externi
    -0.55
     saha
    -0.54
     implique
    -0.54
    POSITIVE LOGITS
     Viene
    0.63
     corsair
    0.61
     ecru
    0.60
     Mónica
    0.59
     Áng
    0.55
     madonna
    0.55
    naphthal
    0.54
     Rubén
    0.54
     Darío
    0.53
     OMITBAD
    0.51
    Activations Density 0.466%

    No Known Activations