© 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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 401
    Prev
    Next
    INDEX
    Explanations

    instances of the word "resign" and its variations

    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
    +0.23
    1.2%
    1777
    +0.11
    0.6%
    421
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    260
    +0.23
    0.02
    1777
    +0.11
    0.02
    1640
    +0.08
    0.01
    Negative Logits
    <bos>
    -2.99
    /***
    
    -0.89
    //});
    -0.73
    };*/
    -0.68
    //};
    -0.63
    })();
    
    -0.62
    //{
    
    -0.60
    },[])
    -0.56
    /*!
    
    -0.56
    /*@
    -0.56
    POSITIVE LOGITS
     resignation
    1.02
     véhic
    0.94
     soulign
    0.93
     resigning
    0.90
    resign
    0.89
     maneu
    0.89
     plong
    0.88
     quoique
    0.84
     resigned
    0.84
     resign
    0.83
    Activations Density 0.029%

    No Known Activations