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. 1090
    Prev
    Next
    INDEX
    Explanations

    phrases related to newsletter subscriptions and delivery

    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
    +0.26
    0.9%
    1343
    +0.17
    0.6%
    453
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1248
    +0.26
    0.04
    350
    +0.17
    0.03
    1403
    +0.10
    0.02
    Negative Logits
    <bos>
    -2.30
    RTEX
    -0.66
    public
    -0.66
    甲
    -0.64
    ,
    -0.63
    لينكات
    -0.63
    ОБ
    -0.63
    alignSelf
    -0.63
    Marshaller
    -0.62
     AssemblyCompany
    -0.62
    POSITIVE LOGITS
     affor
    2.12
     accla
    2.04
     volunte
    2.03
     philanth
    1.99
     michelin
    1.96
     stockholm
    1.95
     fortn
    1.94
     unlaw
    1.94
     increa
    1.91
     lidl
    1.90
    Activations Density 0.073%

    No Known Activations