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. 15639
    Prev
    Next
    INDEX
    Explanations

    phrases related to competitions or tournaments

    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
    455
    +0.10
    0.3%
    1042
    +0.08
    0.2%
    166
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    455
    +0.10
    0.02
    911
    +0.08
    0.03
    1551
    +0.08
    0.03
    Negative Logits
    bindParam
    -0.56
    conectar
    -0.55
    addWidget
    -0.53
    Grüße
    -0.53
    nių
    -0.49
     дописавши
    -0.49
    arschu
    -0.48
    Cuar
    -0.48
    ReusableCell
    -0.47
    uncurkan
    -0.46
    POSITIVE LOGITS
     reluct
    1.30
     depic
    1.24
     unve
    1.21
     indestru
    1.19
     shenan
    1.15
     disreg
    1.14
     impra
    1.13
     encomp
    1.11
     philanth
    1.11
     increa
    1.10
    Activations Density 0.278%

    No Known Activations