© 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. 2738
    Prev
    Next
    INDEX
    Explanations

    names of an individual, specifically "Sharon."

    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
    1178
    +0.14
    0.5%
    1671
    +0.12
    0.4%
    1506
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.14
    0.06
    690
    +0.12
    0.06
    1343
    +0.12
    0.05
    Negative Logits
     thu
    -0.75
    ত
    -0.74
    
    -0.70
     do
    -0.69
     pass
    -0.68
    ർ
    -0.66
    useEffect
    -0.66
    ynb
    -0.66
    JspWriter
    -0.66
     cảm
    -0.66
    POSITIVE LOGITS
     affor
    2.10
     increa
    2.09
     impra
    2.04
     suscep
    2.00
     indestru
    1.96
     emphat
    1.96
     unden
    1.94
     Juf
    1.91
     inev
    1.91
     accla
    1.90
    Activations Density 0.344%

    No Known Activations