© 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. 6-RES-JB
    11. 8979
    Prev
    Next
    INDEX
    Explanations

    references to hair products especially gels

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    1331
    +0.13
    0.6%
    783
    +0.12
    0.6%
    156
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    783
    +0.13
    0.04
    1331
    +0.12
    0.03
    690
    +0.12
    0.03
    Negative Logits
    <bos>
    -1.21
    ClientSize
    -0.70
    SystemColors
    -0.60
     وتسجيلات
    -0.57
    HostException
    -0.54
     Prat
    -0.53
    Mã
    -0.52
    Poznám
    -0.52
    Prat
    -0.51
     burberry
    -0.51
    POSITIVE LOGITS
     Gel
    1.39
     gel
    1.34
    Gel
    1.31
     GEL
    1.15
    gel
    1.11
     gels
    1.07
    Jelly
    1.03
    GEL
    1.00
    gels
    0.95
     Jelly
    0.94
    Activations Density 0.441%

    No Known Activations