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. 5361
    Prev
    Next
    INDEX
    Explanations

    text related to a method of comparing temperature values sensed by sensors, issuing orders based on the values, and conducting additional surveys in a hydraulic fracturing 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
    382
    +0.24
    1.5%
    50
    +0.21
    1.3%
    1535
    +0.17
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.24
    0.30
    2034
    +0.21
    0.25
    2019
    +0.17
    0.16
    Negative Logits
    <bos>
    -4.20
    ⓧ
    -1.43
    /**
    -1.15
    <?
    -1.12
    
    
    -1.08
    /*
    -0.97
     springfox
    -0.96
    ///**
    -0.89
    /*++
    -0.80
    Jeografia
    -0.80
    POSITIVE LOGITS
     maroc
    1.41
     lele
    1.38
     milano
    1.26
     bandung
    1.24
     maneu
    1.24
     wien
    1.18
     ananas
    1.18
     malheureux
    1.16
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.14
     malheure
    1.14
    Activations Density 2.424%

    No Known Activations