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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 804
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas

    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
    +0.28
    1.5%
    1757
    +0.14
    0.7%
    1741
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.28
    0.07
    1757
    +0.14
    0.05
    382
    +0.12
    0.05
    Negative Logits
    <bos>
    -2.76
    ⓧ
    -1.38
    
    
    -1.12
    <?
    -1.05
    <?
    
    -0.96
    /***
    
    -0.84
    /**
    -0.82
     springfox
    -0.74
    },[])
    -0.70
    //});
    -0.69
    POSITIVE LOGITS
     unspeak
    0.68
     maneu
    0.61
     impra
    0.60
     iirc
    0.57
     indescri
    0.57
    Abuse
    0.56
     unexplo
    0.54
     pleins
    0.53
     véhic
    0.53
     beverly
    0.52
    Activations Density 0.296%

    No Known Activations