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. 15747
    Prev
    Next
    INDEX
    Explanations

    terms related to cybersecurity threats and attacks

    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
    876
    +0.19
    0.6%
    1284
    +0.14
    0.4%
    511
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1284
    +0.19
    0.04
    1931
    +0.14
    0.03
    96
    +0.13
    0.01
    Negative Logits
    <bos>
    -1.29
     Demokrat
    -0.60
     المعيارى
    -0.49
     Wali
    -0.49
    لقد
    -0.47
    GraphicsUnit
    -0.46
    Biografi
    -0.46
    |<\
    -0.46
    脚注の使い方
    -0.46
     konserv
    -0.46
    POSITIVE LOGITS
     diffusi
    1.06
     encomp
    1.04
     scrat
    1.03
     guarante
    1.02
     increa
    1.02
     maneu
    0.99
     biex
    0.97
     exciter
    0.97
     overla
    0.96
     suscep
    0.96
    Activations Density 0.400%

    No Known Activations