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

    Neuronpedia

    Jacobian LensNEW
    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. 10943
    Prev
    Next
    INDEX
    Explanations

    verbs related to agreement or consensus between parties

    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
    421
    +0.12
    0.4%
    1573
    +0.12
    0.4%
    889
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1573
    +0.12
    0.03
    421
    +0.12
    0.04
    889
    +0.10
    0.03
    Negative Logits
     praktik
    -0.81
     meras
    -0.79
     Strukt
    -0.72
     stok
    -0.70
     solidar
    -0.69
     papas
    -0.68
     keramik
    -0.65
     kapital
    -0.65
     buta
    -0.65
     kard
    -0.64
    POSITIVE LOGITS
     agree
    1.16
     Agree
    1.15
     Agreed
    1.09
     agreement
    1.07
     agreeing
    1.07
     agreed
    1.03
     agrees
    0.99
     Agreement
    0.99
    Agree
    0.98
    agree
    0.98
    Activations Density 0.075%

    No Known Activations