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. 10-RES-JB
    6. 985
    Prev
    Next
    INDEX
    Explanations

    references to regulatory bodies and laws affecting financial markets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.30
    1.1%
    856
    +0.09
    0.3%
    1870
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.30
    0.05
    1485
    +0.09
    0.05
    1531
    +0.09
    0.05
    Negative Logits
    <bos>
    -2.75
     share
    -0.70
    <b>
    -0.69
     offer
    -0.66
     engage
    -0.65
     distribute
    -0.64
     create
    -0.64
     enjoy
    -0.63
     prepare
    -0.63
     contribute
    -0.63
    POSITIVE LOGITS
     unwarran
    1.72
     Juf
    1.71
     Minang
    1.53
     bandung
    1.49
     ftu
    1.46
     [''
    1.45
     Karang
    1.43
     uncin
    1.43
     reft
    1.42
     embodi
    1.42
    Activations Density 1.029%

    No Known Activations