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. 1344
    Prev
    Next
    INDEX
    Explanations

    mentions of the names "Trump" and "Zuma"

    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
    1978
    +0.14
    0.4%
    1741
    +0.11
    0.3%
    478
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.14
    0.09
    1001
    +0.11
    0.06
    1957
    +0.11
    0.04
    Negative Logits
     initComponents
    -0.72
    Atsauces
    -0.67
     صوتيه
    -0.66
     pesta
    -0.65
     alkoh
    -0.65
     autorytatywna
    -0.64
    पया
    -0.63
    הערות
    -0.63
     melat
    -0.63
    İstinadlar
    -0.63
    POSITIVE LOGITS
     :'(
    0.82
     Whence
    0.82
     lmfao
    0.81
     indestru
    0.80
     hahah
    0.79
     😭😭
    0.78
     himself
    0.77
     outlander
    0.75
     ;-;
    0.74
     madonna
    0.73
    Activations Density 0.460%

    No Known Activations