Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 671
    Prev
    Next
    INDEX
    Explanations

    mentions of medals and achievements

    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
    32
    +0.15
    0.7%
    1339
    +0.14
    0.7%
    938
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.15
    0.03
    1896
    +0.14
    0.02
    1515
    +0.13
    0.02
    Negative Logits
    <bos>
    -1.59
    WebElementEntity
    -0.65
    Personendaten
    -0.62
    illots
    -0.62
     bezeichneter
    -0.60
    nasel
    -0.59
    CodeDom
    -0.59
    Билгалдахарш
    -0.58
     Italijani
    -0.58
     оригіналу
    -0.57
    POSITIVE LOGITS
     medal
    1.08
     Medal
    1.05
    Medal
    1.00
    medal
    0.97
     medals
    0.89
     Medals
    0.81
     medallion
    0.78
     Meda
    0.77
     paradiso
    0.77
     unden
    0.73
    Activations Density 0.439%

    No Known Activations