© 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. 0-RES-JB
    11. 2872
    Prev
    Next
    INDEX
    Explanations

    statements related to political and societal issues, with a focus on critical or questioning perspectives

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    1961
    +0.08
    0.3%
    1438
    +0.06
    0.2%
    1110
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1577
    +0.08
    0.05
    51
    +0.06
    0.04
    1363
    +0.06
    0.04
    Negative Logits
    Descarga
    -0.87
     sur
    -0.80
    Temporada
    -0.79
    Como
    -0.78
    ਿ
    -0.78
     sus
    -0.77
    bar
    -0.77
    Restaurante
    -0.77
    Lugar
    -0.76
    Campo
    -0.76
    POSITIVE LOGITS
     increa
    3.39
     affor
    3.13
     strick
    2.96
     maneu
    2.95
     !...
    2.93
     ?...
    2.91
    <bos>
    2.88
     scrat
    2.88
     :'(
    2.84
     encomp
    2.84
    Activations Density 0.293%

    No Known Activations