© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2649
    Prev
    Next
    INDEX
    Explanations

    terms related to rehabilitation and rehab facilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    866
    +0.17
    0.9%
    1506
    +0.16
    0.8%
    1276
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1276
    +0.17
    0.02
    1870
    +0.16
    0.01
    1506
    +0.15
    0.02
    Negative Logits
    <bos>
    -1.73
    click
    -0.61
     click
    -0.61
    ണ്ട
    -0.59
    ുറ
    -0.58
     gather
    -0.57
    clock
    -0.57
    float
    -0.56
    void
    -0.56
        
    -0.55
    POSITIVE LOGITS
     rehabilitation
    1.15
     unwarran
    1.14
     Rehabilitation
    1.11
     Rehab
    1.10
     liberality
    1.09
     quoique
    1.07
     depic
    1.06
     felicity
    1.06
     disagre
    1.06
     riviera
    1.05
    Activations Density 0.086%

    No Known Activations