© 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. 11900
    Prev
    Next
    INDEX
    Explanations

    the word "given" used in the context of providing or receiving something

    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
    871
    +0.19
    0.7%
    1271
    +0.14
    0.5%
    82
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    871
    +0.19
    0.04
    991
    +0.14
    0.04
    1271
    +0.13
    0.04
    Negative Logits
     désigne
    -0.54
     ujedno
    -0.53
     hjæl
    -0.51
     contribue
    -0.49
     faudrait
    -0.49
     fortæ
    -0.49
     restera
    -0.48
     gøre
    -0.48
     résulte
    -0.46
     devra
    -0.45
    POSITIVE LOGITS
    given
    1.09
     GIVEN
    1.03
     given
    1.03
    Given
    0.95
     Given
    0.94
     giv
    0.90
    giv
    0.79
     GIVE
    0.73
     Giving
    0.67
     Gave
    0.67
    Activations Density 0.094%

    No Known Activations