© 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. 2830
    Prev
    Next
    INDEX
    Explanations

    phrases related to job opportunities, employment positions, and financial support options

    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
    1376
    +0.09
    0.3%
    1107
    +0.08
    0.2%
    1145
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.09
    0.04
    1896
    +0.08
    0.03
    1120
    +0.07
    0.04
    Negative Logits
    ctivos
    -0.59
    au
    -0.56
    Salir
    -0.55
    Enum
    -0.55
    сутствие
    -0.55
    firebase
    -0.55
    iyle
    -0.54
    columns
    -0.54
     au
    -0.54
     Система
    -0.53
    POSITIVE LOGITS
     Hourly
    1.96
     hourly
    1.79
     intermitt
    1.51
    Hourly
    1.50
     michelin
    1.48
    hourly
    1.38
     stockholm
    1.38
     snoopy
    1.36
     accla
    1.34
     outlander
    1.34
    Activations Density 0.329%

    No Known Activations