© 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. 2674
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticism or negative behavior

    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
    168
    +0.09
    0.3%
    251
    +0.08
    0.2%
    1339
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.09
    0.04
    1343
    +0.08
    0.04
    283
    +0.08
    0.01
    Negative Logits
     effe
    -1.08
     encomp
    -1.00
     Cfr
    -0.99
     embra
    -0.96
     pollut
    -0.95
     chery
    -0.95
     claudia
    -0.91
     jorge
    -0.91
     fuf
    -0.91
     stockholm
    -0.90
    POSITIVE LOGITS
    sive
    1.27
    sives
    1.20
     Newswire
    0.90
     spoilers
    0.86
    illin
    0.86
    sively
    0.85
    siveness
    0.84
    taminophen
    0.79
    sivity
    0.79
    diocese
    0.79
    Activations Density 0.366%

    No Known Activations