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. 12-RES-JB
    6. 7876
    Prev
    Next
    INDEX
    Explanations

    discussions about economic hardship and its impact on communities

    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.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.12.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    12
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.42
    1.5%
    604
    +0.14
    0.5%
    752
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.42
    0.08
    752
    +0.14
    0.06
    1703
    +0.10
    0.07
    Negative Logits
    <bos>
    -3.27
     дописавши
    -0.92
     esboço
    -0.70
     Paglinawan
    -0.67
    IsMutable
    -0.64
    AnchorTagHelper
    -0.61
     ModelRenderer
    -0.61
    HomeAsUpEnabled
    -0.60
    isContained
    -0.60
    Panamoan
    -0.60
    POSITIVE LOGITS
     Minang
    1.93
     Karang
    1.68
     bandung
    1.67
     Palembang
    1.65
     Bekasi
    1.63
     Jambi
    1.60
     Banjar
    1.59
     Pekan
    1.49
     Tangerang
    1.47
     jati
    1.46
    Activations Density 0.900%

    No Known Activations