© 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. 3903
    Prev
    Next
    INDEX
    Explanations

    phrases related to legislative processes

    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
    1013
    +0.17
    0.5%
    1177
    +0.14
    0.4%
    1870
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1784
    +0.17
    0.07
    284
    +0.14
    0.07
    1056
    +0.10
    0.07
    Negative Logits
     utop
    -1.00
     tuc
    -0.94
     palab
    -0.91
     solidar
    -0.91
     naran
    -0.90
     impon
    -0.89
     baum
    -0.89
     Okt
    -0.88
     paus
    -0.87
     logis
    -0.87
    POSITIVE LOGITS
     dachshund
    0.72
    jątk
    0.69
     by
    0.69
     ferdig
    0.68
     rascal
    0.67
     shenan
    0.66
     Confira
    0.63
    приєм
    0.61
     subgoals
    0.60
     cuck
    0.59
    Activations Density 0.419%

    No Known Activations