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. 1803
    Prev
    Next
    INDEX
    Explanations

    words related to tracking and analyzing entity counts or occurrences

    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
    0.9%
    1978
    +0.12
    0.5%
    143
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    691
    +0.24
    0.05
    742
    +0.12
    0.04
    1385
    +0.07
    0.07
    Negative Logits
    <bos>
    -3.06
    ⓧ
    -1.01
    SequentialGroup
    -0.78
    Cyfarwyddwr
    -0.78
     AssemblyCompany
    -0.76
    
    
    -0.75
    }],
    
    -0.72
    Referències
    -0.72
    /***
    
    -0.71
    Enllaços
    -0.71
    POSITIVE LOGITS
     bandung
    1.77
     Minang
    1.66
     jaya
    1.58
     Jambi
    1.57
     napoli
    1.54
     riviera
    1.53
     valencia
    1.49
     stockholm
    1.48
     panama
    1.46
     impractica
    1.45
    Activations Density 0.687%

    No Known Activations