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. 727
    Prev
    Next
    INDEX
    Explanations

    terms related to the delivery of services or information

    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
    +0.23
    1.3%
    1034
    +0.10
    0.6%
    1637
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    240
    +0.23
    0.02
    316
    +0.10
    0.02
    1437
    +0.09
    0.02
    Negative Logits
    <bos>
    -2.60
    /***
    
    -0.65
    <?
    
    -0.58
     espec
    -0.58
    cline
    -0.55
    seit
    -0.54
    struct
    -0.54
    /**
    -0.54
    Gost
    -0.53
    ⓧ
    -0.53
    POSITIVE LOGITS
     delivery
    1.23
     DELIVERY
    1.23
     Delivery
    1.22
     Delivered
    1.20
     Deliver
    1.18
     Minang
    1.18
     jaya
    1.15
     bandung
    1.14
     deliveries
    1.11
    delivery
    1.11
    Activations Density 0.059%

    No Known Activations