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. 8339
    Prev
    Next
    INDEX
    Explanations

    phrases related to social and political issues, particularly focusing on women's rights and equality

    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
    674
    +0.36
    1.2%
    1967
    +0.17
    0.6%
    478
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.36
    0.08
    1533
    +0.17
    0.05
    610
    +0.15
    0.09
    Negative Logits
     McLaugh
    -0.76
     heapq
    -0.75
     unspeak
    -0.72
     pymysql
    -0.70
    seperti
    -0.69
    Vrij
    -0.68
     shenan
    -0.67
    mengg
    -0.65
     disreg
    -0.64
     apprehen
    -0.64
    POSITIVE LOGITS
     silikon
    1.17
     alkoh
    1.14
     sopr
    1.13
     Settembre
    1.07
     Luglio
    1.06
     liev
    1.06
     karton
    1.04
     allarg
    1.04
     Ottobre
    1.03
     torba
    1.01
    Activations Density 0.466%

    No Known Activations