© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 4237
    Prev
    Next
    INDEX
    Explanations

    texts related to the potential risks and impacts of advancements in technology, particularly focusing on cybersecurity, autonomous systems, and ethical considerations related to robotics

    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
    604
    +0.12
    0.3%
    872
    +0.09
    0.3%
    674
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1240
    +0.12
    0.05
    1951
    +0.09
    0.04
    1380
    +0.09
    0.01
    Negative Logits
     reluct
    -0.64
     Gorb
    -0.62
     Sted
    -0.62
     ineffec
    -0.62
     McLaugh
    -0.61
     Consolid
    -0.59
     Shakspeare
    -0.58
     fidèle
    -0.58
     Middles
    -0.57
     Reim
    -0.57
    POSITIVE LOGITS
     pavo
    0.63
     ethical
    0.60
     risks
    0.55
     democra
    0.55
     graus
    0.55
     palio
    0.53
     poros
    0.53
     tril
    0.53
     potencial
    0.53
     ethically
    0.52
    Activations Density 0.612%

    No Known Activations