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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14607
    Prev
    Next
    INDEX
    Explanations

    terms related to time urgency and decision-making in a specific context

    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
    690
    +0.17
    0.5%
    284
    +0.10
    0.3%
    1473
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.17
    0.08
    690
    +0.10
    0.05
    1603
    +0.09
    0.05
    Negative Logits
     increa
    -1.46
     practition
    -1.31
     purcha
    -1.30
     guarante
    -1.28
     ?...
    -1.25
     encomp
    -1.25
     🤣🤣
    -1.22
     scrat
    -1.22
     volunte
    -1.21
     desir
    -1.21
    POSITIVE LOGITS
    : 
    0.72
     uska
    0.61
    SharedDtor
    0.59
    ENOMEM
    0.58
     AssemblyCompany
    0.58
     FishBase
    0.57
    styleType
    0.57
    ChildScrollView
    0.57
    onViewCreated
    0.57
    RegressionTest
    0.56
    Activations Density 0.354%

    No Known Activations