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. 718
    Prev
    Next
    INDEX
    Explanations

    phrases related to business partnerships

    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
    752
    +0.18
    0.5%
    227
    +0.17
    0.5%
    50
    +0.17
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.18
    0.07
    752
    +0.17
    0.06
    50
    +0.17
    0.05
    Negative Logits
    .
    -0.70
    되지
    -0.68
    ;
    -0.68
    1
    -0.67
    ."/
    -0.67
    }`).
    -0.67
    ,
    -0.66
    祖
    -0.66
     away
    -0.65
    	
    -0.65
    POSITIVE LOGITS
     Souha
    1.95
     Juf
    1.94
     délib
    1.93
     véhic
    1.80
     Khart
    1.77
     considér
    1.76
     Sén
    1.75
     Confu
    1.75
     philanth
    1.74
     Intere
    1.73
    Activations Density 0.403%

    No Known Activations