© 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. 5515
    Prev
    Next
    INDEX
    Explanations

    phrases related to encouraging and teaching others

    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
    2034
    +0.21
    0.6%
    752
    +0.10
    0.3%
    2019
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.21
    0.05
    1553
    +0.10
    0.05
    1959
    +0.09
    0.05
    Negative Logits
     Præ
    -1.49
     Græ
    -1.39
     suspic
    -1.24
     fatis
    -1.23
     fta
    -1.23
     År
    -1.22
     peculi
    -1.21
     feen
    -1.20
     magis
    -1.20
     Væ
    -1.19
    POSITIVE LOGITS
     don
    0.79
     Make
    0.76
     make
    0.75
     Otherwise
    0.73
     Then
    0.73
     Let
    0.73
     get
    0.72
     Your
    0.72
     create
    0.71
     do
    0.71
    Activations Density 0.364%

    No Known Activations