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. 6888
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to economic measures and social commentary

    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
    +0.19
    0.6%
    2034
    +0.13
    0.5%
    1150
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1934
    +0.19
    0.07
    742
    +0.13
    0.05
    668
    +0.11
    0.06
    Negative Logits
    <bos>
    -3.61
    Autoritní
    -1.05
     Мексичка
    -1.01
     Administrativna
    -0.94
    SourceChecksum
    -0.94
     autorytatywna
    -0.93
     PicClick
    -0.92
    ⓧ
    -0.86
     Roskov
    -0.82
     Italijani
    -0.82
    POSITIVE LOGITS
     unspeak
    0.85
     indestru
    0.85
     shenan
    0.82
     Inhabitants
    0.80
     sophistic
    0.79
     tolerably
    0.79
     indescri
    0.79
     horrend
    0.79
     unwarran
    0.79
     ducato
    0.78
    Activations Density 0.718%

    No Known Activations