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

    Neuronpedia

    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. 6-RES-JB
    11. 5112
    Prev
    Next
    INDEX
    Explanations

    words related to duties, responsibilities, and obligations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.20
    0.8%
    757
    +0.09
    0.3%
    411
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    411
    +0.20
    0.03
    188
    +0.09
    0.03
    251
    +0.09
    0.02
    Negative Logits
    <bos>
    -2.43
    
    -1.00
    /**
    -0.95
    /***
    -0.95
    <?
    -0.88
    ⓧ
    -0.87
     disbur
    -0.78
    //*/
    -0.77
    <?
    -0.77
     intersper
    -0.77
    POSITIVE LOGITS
     obligation
    1.17
     obligations
    1.12
     responsibility
    1.06
     duty
    1.06
     duties
    1.04
     respon
    1.02
    duty
    0.97
     Duty
    0.94
    obligation
    0.92
    Duty
    0.91
    Activations Density 0.278%

    No Known Activations