© 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. 5891
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and disparities in education quality

    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
    184
    +0.17
    0.5%
    198
    +0.15
    0.4%
    394
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.17
    0.03
    1553
    +0.15
    0.06
    1531
    +0.11
    0.04
    Negative Logits
    <bos>
    -1.11
     affor
    -0.98
     Souha
    -0.97
     reluct
    -0.94
     philanth
    -0.91
     shenan
    -0.91
     uninten
    -0.90
     inev
    -0.88
     ecru
    -0.85
     rafra
    -0.82
    POSITIVE LOGITS
     lack
    0.69
     lacked
    0.66
    lack
    0.62
     lacks
    0.61
    nadequate
    0.61
     lacking
    0.60
     improper
    0.60
     inadequate
    0.59
     insufficient
    0.57
     missing
    0.56
    Activations Density 0.624%

    No Known Activations