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. 6879
    Prev
    Next
    INDEX
    Explanations

    references to technological trends and their implications on consumer behavior

    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
    +0.35
    1.3%
    198
    +0.16
    0.6%
    752
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.35
    0.09
    102
    +0.16
    0.05
    1977
    +0.10
    0.07
    Negative Logits
    <bos>
    -2.82
     mustered
    -0.63
    ⓧ
    -0.62
    дивиду
    -0.60
     would
    -0.60
     cooperated
    -0.60
     proceeded
    -0.58
     convene
    -0.57
     detain
    -0.57
     prayed
    -0.57
    POSITIVE LOGITS
     bandung
    1.39
     lele
    1.23
     Bekasi
    1.12
     valencia
    1.11
     Minang
    1.11
     Banjar
    1.10
     jaya
    1.10
     jawa
    1.10
     Palembang
    1.09
     gila
    1.09
    Activations Density 1.286%

    No Known Activations