© 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. 8370
    Prev
    Next
    INDEX
    Explanations

    terms related to electric vehicles and public transportation systems

    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
    1.0%
    1385
    +0.09
    0.3%
    1842
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1405
    +0.24
    0.06
    694
    +0.09
    0.05
    41
    +0.07
    0.05
    Negative Logits
    <bos>
    -2.52
    ⓧ
    -0.81
    ///**
    -0.72
    /**
    -0.68
    
    -0.68
    /*
    -0.67
     елның
    -0.64
     SEDS
    -0.63
    lccn
    -0.63
    //-->
    -0.62
    POSITIVE LOGITS
     Juf
    1.44
     Intere
    1.22
     Keny
    1.19
     Confu
    1.18
     soulign
    1.16
     impra
    1.15
     Minang
    1.14
     unspeak
    1.14
     practition
    1.14
     hentai
    1.13
    Activations Density 0.498%

    No Known Activations