© 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. 6-RES-JB
    11. 6293
    Prev
    Next
    INDEX
    Explanations

    words related to financial matters or transactions

    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
    184
    +0.40
    2.1%
    394
    +0.28
    1.4%
    1741
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.40
    0.02
    1385
    +0.28
    0.09
    394
    +0.13
    0.08
    Negative Logits
    <bos>
    -4.31
    Autoritní
    -1.25
    Билгалдахарш
    -1.16
    GEBURTSDATUM
    -1.05
    /**
    -1.05
    
    -1.04
     Italijani
    -1.03
    Vidite
    -1.03
    contentLoaded
    -1.01
    脚注の使い方
    -0.99
    POSITIVE LOGITS
     aen
    0.96
     umo
    0.95
     eorum
    0.95
     vne
    0.95
     habet
    0.94
     potest
    0.93
     ejus
    0.89
     marta
    0.88
     haup
    0.88
     nuoc
    0.88
    Activations Density 1.090%

    No Known Activations