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. 15730
    Prev
    Next
    INDEX
    Explanations

    phrases related to catastrophic scenarios or potential dangers

    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
    814
    +0.10
    0.3%
    2000
    +0.09
    0.2%
    674
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    814
    +0.10
    0.03
    2032
    +0.09
    0.04
    703
    +0.08
    0.03
    Negative Logits
     disagre
    -1.44
     reluct
    -1.27
     inev
    -1.26
     inappro
    -1.25
     berea
    -1.23
     maneu
    -1.23
     unwarran
    -1.23
     gaily
    -1.23
     increa
    -1.21
     depic
    -1.21
    POSITIVE LOGITS
    <bos>
    0.88
     Insee
    0.56
    thâu
    0.56
    Hiện
    0.56
    Ārējās
    0.56
     Audiodateien
    0.56
    BeginInit
    0.55
     understood
    0.55
    rrggbb
    0.54
    Được
    0.54
    Activations Density 0.178%

    No Known Activations