© 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. 3845
    Prev
    Next
    INDEX
    Explanations

    specific terms related to legal documents, insurance, policies, and claims

    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
    +0.22
    1.4%
    381
    +0.13
    0.8%
    1535
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1145
    +0.22
    0.11
    381
    +0.13
    0.05
    1535
    +0.11
    0.07
    Negative Logits
    <bos>
    -4.03
    ⓧ
    -1.40
    /**
    -1.01
    <?
    -1.00
    
    -0.92
     springfox
    -0.91
    /*++
    -0.91
    /*
    -0.85
     AssemblyCompany
    -0.73
     continue
    -0.73
    POSITIVE LOGITS
     aen
    1.97
     Juf
    1.92
     lele
    1.89
     wien
    1.87
     mef
    1.83
     effe
    1.80
     fta
    1.80
     Manufact
    1.80
     délib
    1.78
     increa
    1.77
    Activations Density 0.712%

    No Known Activations