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. 14598
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to characteristics of different entities or programs

    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
    687
    +0.14
    0.6%
    68
    +0.12
    0.5%
    1839
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1839
    +0.14
    0.04
    68
    +0.12
    0.03
    468
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.34
    /***
    
    -0.94
    Referencie
    -0.68
    <>
    
    -0.65
    ///**
    -0.64
    Odkazy
    -0.61
    Vegeu
    -0.61
     ajudá
    -0.60
    Iné
    -0.60
    Linki
    -0.58
    POSITIVE LOGITS
     characteristics
    1.22
     Characteristics
    1.20
     wien
    1.18
     effe
    1.16
     meis
    1.16
     thut
    1.15
     Characteristic
    1.14
     fatis
    1.14
     ftu
    1.12
     waer
    1.11
    Activations Density 0.297%

    No Known Activations