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. 15733
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflicts of interest

    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
    223
    +0.09
    0.3%
    1120
    +0.07
    0.2%
    1150
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.09
    0.03
    1948
    +0.07
    0.04
    1571
    +0.07
    0.02
    Negative Logits
     impra
    -1.31
     indestru
    -1.25
     reluct
    -1.19
     increa
    -1.17
     impractica
    -1.15
     disagre
    -1.12
     uninten
    -1.09
     unwarran
    -1.08
     excru
    -1.06
     hairc
    -1.05
    POSITIVE LOGITS
     CreateTagHelper
    0.65
    MessageTagHelper
    0.65
     ethical
    0.64
     ética
    0.60
    RuleContext
    0.59
    ethics
    0.59
     незавершена
    0.58
     saites
    0.57
    HtmlAttribute
    0.56
    StoryboardSegue
    0.56
    Activations Density 0.484%

    No Known Activations