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. 6048
    Prev
    Next
    INDEX
    Explanations

    keywords related to chemical weapons in the context of military conflict and international conventions

    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
    1416
    +0.14
    0.7%
    50
    +0.14
    0.6%
    789
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1416
    +0.14
    0.03
    1290
    +0.14
    0.03
    789
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.79
    ⓧ
    -0.71
    public
    -0.63
    PerformLayout
    -0.60
    /**
    -0.59
     distribute
    -0.58
     mobilize
    -0.58
    autorest
    -0.57
     onView
    -0.57
    USTAIN
    -0.56
    POSITIVE LOGITS
     soulign
    1.23
     véhic
    1.17
     quoique
    1.13
     unwarran
    1.13
     considér
    1.12
     murano
    1.07
     désol
    1.07
     ecru
    1.05
     réfugi
    1.03
     mikrofon
    1.02
    Activations Density 0.103%

    No Known Activations