© 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. 14722
    Prev
    Next
    INDEX
    Explanations

    words related to gratitude and support

    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
    946
    +0.09
    0.3%
    1129
    +0.09
    0.2%
    1600
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1600
    +0.09
    0.04
    1129
    +0.09
    0.05
    1252
    +0.08
    0.03
    Negative Logits
     squa
    -1.05
     disagre
    -1.04
     glau
    -1.04
     affor
    -1.03
     haup
    -1.03
     oleo
    -1.02
     leonardo
    -1.01
     effe
    -1.01
     maer
    -1.00
     inev
    -1.00
    POSITIVE LOGITS
     support
    0.81
    ISupport
    0.80
     supportive
    0.76
    support
    0.74
    Support
    0.70
     solidarity
    0.70
    upport
    0.67
     Support
    0.67
     supports
    0.65
     donations
    0.65
    Activations Density 0.335%

    No Known Activations