© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 3634
    Prev
    Next
    INDEX
    Explanations

    phrases related to family relationships

    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
    +0.24
    0.9%
    513
    +0.08
    0.3%
    1081
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1598
    +0.24
    0.07
    513
    +0.08
    0.06
    825
    +0.07
    0.07
    Negative Logits
    <bos>
    -3.08
     intersper
    -0.97
    /**
    -0.92
    <?
    -0.88
    ⓧ
    -0.87
    /***
    -0.86
    
    -0.82
     endow
    -0.81
     disbur
    -0.79
     strode
    -0.79
    POSITIVE LOGITS
     Rois
    0.95
     paillettes
    0.90
     Chinois
    0.84
     Mère
    0.81
     marea
    0.80
     miniatura
    0.80
     papillon
    0.78
    poir
    0.78
     monaster
    0.78
     Sén
    0.77
    Activations Density 1.352%

    No Known Activations