Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 5421
    Prev
    Next
    INDEX
    Explanations

    negative predictions about the future

    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
    2034
    +0.17
    0.7%
    50
    +0.15
    0.7%
    1150
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1473
    +0.17
    0.06
    2034
    +0.15
    0.08
    897
    +0.11
    0.06
    Negative Logits
    <bos>
    -3.03
    /***
    
    -0.65
    ///**
    -0.65
    дмила
    -0.63
    /*++
    -0.62
    /*!
    
    -0.62
    Autoritní
    -0.58
    axs
    -0.58
    حوالہ
    -0.57
    squareup
    -0.56
    POSITIVE LOGITS
     maneu
    1.20
     kaos
    1.14
     kase
    1.13
     maroc
    1.11
     hilux
    1.09
     disreg
    1.08
     maske
    1.07
     tupperware
    1.06
     juventus
    1.06
     kasa
    1.06
    Activations Density 1.121%

    No Known Activations