Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 14801
    Prev
    Next
    INDEX
    Explanations

    references to geopolitical tensions and military activities

    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
    1343
    +0.13
    0.4%
    198
    +0.13
    0.4%
    613
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    613
    +0.13
    0.06
    1997
    +0.13
    0.05
    227
    +0.11
    0.06
    Negative Logits
     tarte
    -0.68
     tupperware
    -0.67
     kaffe
    -0.67
     bandung
    -0.67
     herbes
    -0.67
     frites
    -0.66
     tricot
    -0.66
     boxe
    -0.66
     fusible
    -0.66
     roux
    -0.65
    POSITIVE LOGITS
     newspaper
    0.70
     Bartholo
    0.69
     Rine
    0.68
     Middles
    0.66
     renforcé
    0.65
     newspapers
    0.65
     Gorb
    0.65
     pamph
    0.63
    AllAfrica
    0.63
     Rued
    0.63
    Activations Density 0.301%

    No Known Activations