© 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. 0-RES-JB
    11. 1057
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing a preference or intention

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.22
    1.6%
    2019
    +0.08
    0.6%
    1334
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1334
    +0.22
    0.10
    395
    +0.08
    0.07
    1419
    +0.06
    0.02
    Negative Logits
    <bos>
    -3.59
    ⓧ
    -1.38
    /**
    -1.34
    <?
    -1.22
    
    -1.18
    /*
    -1.05
    /***
    -0.90
    <?
    -0.88
    ///**
    -0.84
    /*++
    -0.81
    POSITIVE LOGITS
     maneu
    1.88
     affor
    1.80
     impra
    1.75
     stockholm
    1.73
     increa
    1.73
     lidl
    1.64
     reluct
    1.62
     volunte
    1.61
     accla
    1.61
     inev
    1.60
    Activations Density 0.894%

    No Known Activations