© 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. 4069
    Prev
    Next
    INDEX
    Explanations

    phrases related to professional wrestling

    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
    478
    +0.10
    0.3%
    513
    +0.08
    0.2%
    1835
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.10
    0.05
    974
    +0.08
    0.03
    1542
    +0.07
    0.03
    Negative Logits
     accla
    -1.06
     inappro
    -0.97
     excru
    -0.96
     toledo
    -0.95
     vns
    -0.94
     reluct
    -0.93
     shenan
    -0.93
     wien
    -0.92
     Juf
    -0.92
     maneu
    -0.92
    POSITIVE LOGITS
     intent
    0.75
     intention
    0.63
     intend
    0.60
    intent
    0.60
     intentions
    0.57
     indeed
    0.56
     intends
    0.54
     intended
    0.52
     pinulongan
    0.51
    minente
    0.51
    Activations Density 0.499%

    No Known Activations