© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14709
    Prev
    Next
    INDEX
    Explanations

    phrases related to employment and workplace issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1573
    +0.16
    0.6%
    241
    +0.14
    0.5%
    597
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1573
    +0.16
    0.03
    241
    +0.14
    0.02
    196
    +0.12
    0.02
    Negative Logits
     macrop
    -0.62
     impractica
    -0.60
     inext
    -0.59
     muco
    -0.57
     indor
    -0.51
     laminar
    -0.51
     reluct
    -0.50
     disgra
    -0.49
     concier
    -0.49
     unden
    -0.48
    POSITIVE LOGITS
     employment
    1.29
     Employment
    1.20
    employment
    1.07
     employ
    1.04
    Employment
    1.02
     employed
    1.00
    employ
    0.97
     employs
    0.91
    employed
    0.90
     employing
    0.88
    Activations Density 0.052%

    No Known Activations