© 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. 4850
    Prev
    Next
    INDEX
    Explanations

    themes related to media critiques and the impact of public perception

    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
    1150
    +0.20
    0.8%
    50
    +0.19
    0.8%
    2034
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.20
    0.13
    1013
    +0.19
    0.14
    2034
    +0.15
    0.12
    Negative Logits
    <bos>
    -2.78
     intersper
    -1.85
     fuf
    -1.61
     emphat
    -1.58
     increa
    -1.50
     encomp
    -1.50
     ?...
    -1.49
     purcha
    -1.47
     !...
    -1.44
     guarante
    -1.42
    POSITIVE LOGITS
    cautionary
    0.79
    abancı
    0.76
    angering
    0.76
    CAUTIONS
    0.70
    requently
    0.69
    gruntled
    0.68
    ."\
    0.68
     ElevatedButton
    0.68
    astrous
    0.68
    appointing
    0.67
    Activations Density 1.210%

    No Known Activations