© 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 EvalsExportsinterp-engineNEWAPI 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. 5298
    Prev
    Next
    INDEX
    Explanations

    mentions and discussions related to office environments, workstations, and office furniture

    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
    1403
    +0.10
    0.3%
    1870
    +0.10
    0.3%
    1385
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1948
    +0.10
    0.05
    1336
    +0.10
    0.05
    1553
    +0.09
    0.06
    Negative Logits
     volunte
    -1.72
     ftu
    -1.70
     thut
    -1.69
     increa
    -1.68
     fta
    -1.65
     desir
    -1.64
     unden
    -1.59
     guarante
    -1.58
     inev
    -1.57
     affor
    -1.57
    POSITIVE LOGITS
     workplace
    1.15
     employees
    1.02
     office
    1.02
     employers
    1.02
     employee
    1.01
     employer
    0.99
     offices
    0.96
     Employees
    0.95
     Workplace
    0.93
     workplaces
    0.91
    Activations Density 0.745%

    No Known Activations