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. 6892
    Prev
    Next
    INDEX
    Explanations

    statistical references to rates and numbers, particularly related to crime and incarceration

    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
    0.8%
    1978
    +0.12
    0.4%
    1385
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1747
    +0.23
    0.03
    539
    +0.12
    0.03
    1978
    +0.10
    0.03
    Negative Logits
    <bos>
    -2.44
     intersper
    -0.77
    ⓧ
    -0.70
    <?
    
    -0.65
    
    
    -0.62
     inaugurate
    -0.62
    /*!
    
    -0.62
     disbur
    -0.59
     harmonize
    -0.58
     acquaint
    -0.56
    POSITIVE LOGITS
     bandung
    1.12
     jaya
    0.96
     jawa
    0.94
     seksi
    0.89
     Minang
    0.82
     Jambi
    0.82
     gila
    0.82
     jati
    0.81
     hcm
    0.81
     surabaya
    0.81
    Activations Density 0.078%

    No Known Activations