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. 14674
    Prev
    Next
    INDEX
    Explanations

    mentions of specific events or actions in a narrative context

    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
    +0.25
    1.5%
    382
    +0.19
    1.2%
    1535
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.25
    0.28
    2034
    +0.19
    0.24
    1535
    +0.17
    0.12
    Negative Logits
    <bos>
    -3.80
    ⓧ
    -1.12
    <?
    -1.06
    /**
    -1.05
    
    
    -0.96
    /***
    
    -0.84
     intersper
    -0.84
     endow
    -0.84
    ///**
    -0.80
    /*++
    -0.78
    POSITIVE LOGITS
     lele
    1.01
     marea
    0.99
     seksi
    0.91
     maroc
    0.88
     ados
    0.87
     ananas
    0.85
     kapsul
    0.85
     multicolore
    0.81
     bambu
    0.81
     jawa
    0.79
    Activations Density 2.193%

    No Known Activations