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. 14818
    Prev
    Next
    INDEX
    Explanations

    phrases related to astronomy and space exploration

    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
    1896
    +0.18
    0.8%
    597
    +0.14
    0.6%
    1335
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    860
    +0.18
    0.03
    1896
    +0.14
    0.03
    1987
    +0.13
    0.04
    Negative Logits
    <bos>
    -1.64
    ⓧ
    -0.74
    
    
    -0.68
    /**
    -0.57
    jsoup
    -0.55
    бият
    -0.54
    ActionMode
    -0.53
    Geplaatst
    -0.51
    <?
    -0.51
    RectangleBorder
    -0.51
    POSITIVE LOGITS
     Karang
    0.94
     tromper
    0.87
     Bintang
    0.86
     malheure
    0.84
     malheureux
    0.84
     nikah
    0.83
     Pekan
    0.83
     sovere
    0.83
     astronomy
    0.80
     abband
    0.79
    Activations Density 0.260%

    No Known Activations