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. 6-RES-JB
    6. 6141
    Prev
    Next
    INDEX
    Explanations

    phrases related to tropical regions and climate

    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
    1103
    +0.16
    0.8%
    1044
    +0.16
    0.8%
    1387
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.16
    0.04
    314
    +0.16
    0.03
    1044
    +0.13
    0.04
    Negative Logits
    <bos>
    -1.13
    ⓧ
    -0.66
    ResponseWriter
    -0.62
    RepeatedField
    -0.62
    RTSC
    -0.61
    djangoproject
    -0.60
    มาะ
    -0.59
     estekak
    -0.57
     ob
    -0.57
    šech
    -0.56
    POSITIVE LOGITS
     pymysql
    1.33
     Tropical
    1.33
    Tropical
    1.30
     tropical
    1.25
     Abbé
    1.22
     rafra
    1.21
     gaily
    1.21
     fays
    1.17
    tropical
    1.17
     Juf
    1.16
    Activations Density 0.379%

    No Known Activations