© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 2050
    Prev
    Next
    INDEX
    Explanations

    political terms and statements related to international affairs

    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
    599
    +0.15
    0.5%
    604
    +0.14
    0.4%
    344
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    915
    +0.15
    0.07
    1499
    +0.14
    0.08
    1001
    +0.10
    0.06
    Negative Logits
     swarovski
    -1.49
     increa
    -1.44
     affor
    -1.37
     peppa
    -1.34
     hairc
    -1.34
     intersper
    -1.32
     effe
    -1.32
     fuf
    -1.32
     encomp
    -1.31
     disagre
    -1.31
    POSITIVE LOGITS
    PreferredItem
    0.64
     Italijanski
    0.62
    hoeddwyd
    0.60
     diplomatic
    0.59
     diplomats
    0.58
     Италијани
    0.57
    Gweler
    0.55
     embassy
    0.54
     diplomacy
    0.53
     gynhyrchwyd
    0.53
    Activations Density 0.958%

    No Known Activations