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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15204
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of inheritance, specifically in the context of passing down traits or characteristics

    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
    1506
    +0.16
    0.8%
    1065
    +0.15
    0.8%
    1961
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.16
    0.05
    478
    +0.15
    0.03
    1065
    +0.15
    0.04
    Negative Logits
    <bos>
    -1.06
    DisplayMetrics
    -0.72
    CodeDom
    -0.72
    case
    -0.69
    displaystyle
    -0.67
    সং
    -0.67
    প
    -0.66
    Prueba
    -0.66
    ে
    -0.65
    core
    -0.65
    POSITIVE LOGITS
     milf
    1.87
     michelin
    1.87
     inev
    1.84
     shenan
    1.84
     hentai
    1.82
     maneu
    1.80
     depic
    1.78
     scrat
    1.77
     intermitt
    1.75
     peppa
    1.75
    Activations Density 0.623%

    No Known Activations