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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 8285
    Prev
    Next
    INDEX
    Explanations

    references to the conflict in Syria in different contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1416
    +0.19
    0.7%
    1491
    +0.14
    0.5%
    555
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1416
    +0.19
    0.06
    1491
    +0.14
    0.04
    1464
    +0.13
    0.04
    Negative Logits
    <bos>
    -0.85
    PerformLayout
    -0.58
    WriteBarrier
    -0.58
     conlle
    -0.50
     NKC
    -0.49
     AUF
    -0.48
    Тру
    -0.48
    Hå
    -0.46
    ceptives
    -0.46
    lielmo
    -0.46
    POSITIVE LOGITS
     Syria
    1.09
     Syrian
    0.99
    Syria
    0.95
     Syrians
    0.92
     Sycamore
    0.85
     Siria
    0.76
     Darío
    0.76
    Sy
    0.75
     Sy
    0.75
     Sykes
    0.69
    Activations Density 0.066%

    No Known Activations