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. 6731
    Prev
    Next
    INDEX
    Explanations

    phrases related to loss, regret, or farewell sentiments

    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
    +0.28
    1.0%
    453
    +0.13
    0.5%
    1150
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    605
    +0.28
    0.02
    16
    +0.13
    0.07
    1150
    +0.13
    0.03
    Negative Logits
    <bos>
    -1.61
     intersper
    -1.26
     encomp
    -1.11
     disbur
    -0.98
     guarante
    -0.89
     endow
    -0.88
     endeavored
    -0.85
     increa
    -0.85
     endeavouring
    -0.84
     strove
    -0.84
    POSITIVE LOGITS
     him
    0.85
     Wikiquote
    0.84
     كومونز
    0.83
    yticks
    0.77
     Wikisource
    0.74
    hdys
    0.74
     BIBSYS
    0.73
     NKC
    0.72
    Mə
    0.72
    Biografía
    0.70
    Activations Density 0.814%

    No Known Activations