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. 14902
    Prev
    Next
    INDEX
    Explanations

    information related to education, specifically focusing on teaching and coaching skills

    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
    +0.17
    0.8%
    1741
    +0.16
    0.8%
    2019
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.17
    0.11
    353
    +0.16
    0.08
    1694
    +0.15
    0.05
    Negative Logits
    <bos>
    -2.27
    /**
    -0.87
    EndGlobalSection
    -0.81
    USTAIN
    -0.79
    raught
    -0.78
    /*
    -0.77
    ATELL
    -0.74
    ⓧ
    -0.74
    <?
    -0.73
    ceptre
    -0.72
    POSITIVE LOGITS
     Kategor
    1.21
     catég
    1.07
     véhic
    1.01
     Ferdin
    0.98
     vôtre
    0.97
     épu
    0.96
     nôtre
    0.95
     moza
    0.95
     opport
    0.94
     Simult
    0.94
    Activations Density 1.458%

    No Known Activations