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. 895
    Prev
    Next
    INDEX
    Explanations

    descriptions and details about accommodations, including views and room amenities

    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
    1.0%
    1385
    +0.09
    0.3%
    690
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    906
    +0.25
    0.01
    1013
    +0.09
    0.05
    1385
    +0.09
    0.05
    Negative Logits
    <bos>
    -2.37
    ⓧ
    -1.25
    <?
    -1.20
    /**
    -1.15
    
    
    -1.08
    /*
    -0.96
    <?
    
    -0.84
    #
    -0.82
    RemoveField
    -0.74
    /***
    
    -0.73
    POSITIVE LOGITS
     tupperware
    1.31
     oleo
    1.28
     scrat
    1.28
     chrysler
    1.28
     maneu
    1.24
     lamborghini
    1.24
     swarovski
    1.23
     bordeaux
    1.20
     malheureux
    1.20
     bosch
    1.18
    Activations Density 0.406%

    No Known Activations