© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12780
    Prev
    Next
    INDEX
    Explanations

    phrases related to architecture and design concepts

    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
    1870
    +0.13
    0.5%
    687
    +0.12
    0.4%
    196
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1705
    +0.13
    0.02
    196
    +0.12
    0.01
    1363
    +0.11
    0.01
    Negative Logits
    CONCLUS
    -0.57
     تضيفلها
    -0.56
    Série
    -0.52
    Matériel
    -0.51
    Matériau
    -0.51
    Puissance
    -0.50
    Bibliografie
    -0.50
    Conclusão
    -0.48
    Caracteristici
    -0.48
    Spécifications
    -0.48
    POSITIVE LOGITS
     architecture
    1.27
     Architecture
    1.19
     architectures
    1.17
    Architecture
    1.12
     architect
    1.09
    architecture
    1.07
     ARCHITECTURE
    1.07
     architects
    1.07
     Architect
    1.04
     architectural
    1.00
    Activations Density 0.044%

    No Known Activations