© 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. 2884
    Prev
    Next
    INDEX
    Explanations

    phrases related to website links

    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
    1506
    +0.09
    0.3%
    1059
    +0.09
    0.3%
    971
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1059
    +0.09
    0.03
    1343
    +0.09
    0.03
    300
    +0.09
    0.03
    Negative Logits
    <bos>
    -0.83
     gøre
    -0.76
     dintr
    -0.71
     împreună
    -0.70
     destul
    -0.67
     gør
    -0.65
     tæn
    -0.62
     potrivit
    -0.62
    AMPLES
    -0.61
    INERY
    -0.60
    POSITIVE LOGITS
     Pe
    2.51
    Pe
    2.34
     pe
    2.26
    pe
    2.13
     PE
    1.97
    PE
    1.79
     Peti
    1.65
     maneu
    1.49
     Peta
    1.48
     pei
    1.45
    Activations Density 0.193%

    No Known Activations