© 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. 4832
    Prev
    Next
    INDEX
    Explanations

    words related to entertainment events and activities

    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
    678
    +0.11
    0.4%
    108
    +0.10
    0.3%
    1959
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.11
    0.08
    1314
    +0.10
    0.08
    1551
    +0.09
    0.05
    Negative Logits
    URLEncoder
    -0.70
    TextWatcher
    -0.60
    Itoa
    -0.59
    FailureListener
    -0.58
    Đây
    -0.58
    Synonymes
    -0.58
    Economía
    -0.57
    Demografía
    -0.56
    IsNullOrEmpty
    -0.55
    Cách
    -0.55
    POSITIVE LOGITS
     impra
    1.69
     reluct
    1.65
     encomp
    1.60
     inev
    1.59
     indestru
    1.59
     emphat
    1.58
     unden
    1.55
     disagre
    1.54
     shenan
    1.51
     maneu
    1.51
    Activations Density 1.499%

    No Known Activations