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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1159
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "left," particularly in political or ideological contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.24
    1.5%
    481
    +0.17
    1.0%
    1480
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.24
    0.06
    1480
    +0.17
    0.04
    1805
    +0.12
    0.04
    Negative Logits
    <bos>
    -2.77
    RouterModule
    -0.73
    /***
    
    -0.69
    paddingVertical
    -0.67
    <>
    
    -0.66
    })();
    
    -0.63
    Diweddarwch
    -0.63
    //};
    -0.61
    MatInputModule
    -0.61
    },{
    
    -0.60
    POSITIVE LOGITS
     accla
    1.24
     Hez
    1.18
     eft
    1.15
     Righ
    1.15
     maneu
    1.14
     leaft
    1.12
     stockholm
    1.12
     lidl
    1.10
     affor
    1.10
     Eft
    1.09
    Activations Density 0.045%

    No Known Activations