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. 14015
    Prev
    Next
    INDEX
    Explanations

    references to the element iron and related terms such as anemia and Iron Lady

    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
    687
    +0.18
    0.8%
    67
    +0.17
    0.7%
    501
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.18
    0.03
    687
    +0.17
    0.03
    196
    +0.13
    0.02
    Negative Logits
     autorytatywna
    -0.50
    setVerticalGroup
    -0.49
    Controllo
    -0.47
    Scénario
    -0.44
    initializeApp
    -0.44
    Hopkins
    -0.43
    ثيق
    -0.43
    SizeF
    -0.42
     Factbook
    -0.42
    ventude
    -0.42
    POSITIVE LOGITS
     Iron
    1.42
    Iron
    1.40
     iron
    1.37
     IRON
    1.36
    iron
    1.32
    IRON
    1.25
     irons
    1.07
     Irons
    1.03
     ironing
    0.91
     hierro
    0.81
    Activations Density 0.076%

    No Known Activations