© 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 EvalsExportsinterp-engineNEWAPI 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. 15189
    Prev
    Next
    INDEX
    Explanations

    phrases related to society, responsibility, and duty

    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
    872
    +0.14
    0.4%
    1445
    +0.13
    0.4%
    1892
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1892
    +0.14
    0.06
    1265
    +0.13
    0.05
    390
    +0.11
    0.06
    Negative Logits
     ftu
    -1.36
     haer
    -1.29
     lele
    -1.28
     ftate
    -1.27
     ftre
    -1.27
     paff
    -1.23
     ufe
    -1.23
     magis
    -1.22
     fta
    -1.22
     vns
    -1.19
    POSITIVE LOGITS
     therefore
    0.92
     hence
    0.81
     this
    0.79
     thats
    0.79
     consequently
    0.76
     thus
    0.75
     it
    0.75
     if
    0.74
     yet
    0.74
     that
    0.73
    Activations Density 0.246%

    No Known Activations