© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4926
    Prev
    Next
    INDEX
    Explanations

    information related to upcoming film releases, particularly focusing on titles and their release details

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.29
    1.1%
    856
    +0.16
    0.6%
    453
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1042
    +0.29
    0.04
    1403
    +0.16
    0.02
    690
    +0.14
    0.03
    Negative Logits
    <bos>
    -2.02
    ⓧ
    -0.96
     onStop
    -0.82
    
    -0.78
     viewWillAppear
    -0.77
    <?
    -0.68
    ByVersion
    -0.67
    <?
    -0.66
     viewDid
    -0.65
    /***
    -0.64
    POSITIVE LOGITS
     maneu
    1.55
     reluct
    1.39
     affor
    1.38
     disagre
    1.33
     shenan
    1.30
     increa
    1.30
     accla
    1.28
     impra
    1.27
     unspeak
    1.27
     strick
    1.26
    Activations Density 0.436%

    No Known Activations