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

    Neuronpedia

    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. 4619
    Prev
    Next
    INDEX
    Explanations

    adjectives related to cognitive or emotional states

    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
    896
    +0.16
    0.6%
    1137
    +0.11
    0.4%
    1937
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.16
    0.07
    1137
    +0.11
    0.07
    896
    +0.11
    0.03
    Negative Logits
    PerformLayout
    -0.69
     kuk
    -0.64
    Prin
    -0.63
     kac
    -0.62
    Tren
    -0.59
    Kuk
    -0.59
     kuli
    -0.57
    Pus
    -0.57
     kuku
    -0.56
    UnitTesting
    -0.56
    POSITIVE LOGITS
     withal
    1.16
     unspeak
    1.08
     cytoplas
    1.08
     fometimes
    1.07
     Shakspeare
    1.06
     tolerably
    1.05
     unwarran
    1.05
     gaily
    1.04
     anhyd
    1.04
     lakers
    1.03
    Activations Density 0.583%

    No Known Activations