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. 5437
    Prev
    Next
    INDEX
    Explanations

    information related to sports events, particularly all-star games

    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
    +0.18
    0.6%
    1323
    +0.11
    0.4%
    703
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.18
    0.03
    1701
    +0.11
    0.02
    2005
    +0.07
    0.02
    Negative Logits
    <bos>
    -2.51
    SequentialGroup
    -0.78
    <>
    
    -0.78
    }{||
    -0.71
    afterEach
    -0.68
    /***
    
    -0.67
    HasAnnotation
    -0.65
    ]--;
    -0.64
     jsPsych
    -0.64
    ////////////
    -0.62
    POSITIVE LOGITS
     Khart
    1.40
     meis
    1.39
     mef
    1.38
     maneu
    1.33
     fta
    1.32
     increa
    1.32
     alre
    1.31
     inev
    1.30
     fup
    1.29
     maer
    1.28
    Activations Density 0.128%

    No Known Activations