© 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. 2781
    Prev
    Next
    INDEX
    Explanations

    words related to honors and achievements

    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
    757
    +0.10
    0.3%
    1335
    +0.09
    0.3%
    341
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.10
    0.05
    1363
    +0.09
    0.04
    1120
    +0.09
    0.04
    Negative Logits
    omaterial
    -0.63
    ostructures
    -0.61
    mkdirs
    -0.60
     Nebenwirkungen
    -0.59
     among
    -0.58
    WriteBarrier
    -0.57
     amongst
    -0.57
     переписи
    -0.57
    titleMargin
    -0.56
     актриса
    -0.56
    POSITIVE LOGITS
    hon
    2.09
    Hon
    1.49
     Simult
    1.44
     Hon
    1.43
     véhic
    1.34
    HON
    1.29
     peppa
    1.28
     HON
    1.28
     confé
    1.27
     versace
    1.26
    Activations Density 0.322%

    No Known Activations