© 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. 6842
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports events and actions

    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
    906
    +0.14
    0.4%
    674
    +0.11
    0.3%
    1842
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.14
    0.05
    1419
    +0.11
    0.03
    1313
    +0.09
    0.03
    Negative Logits
     gmbh
    -1.34
     „,
    -1.32
     ?...
    -1.31
     embodi
    -1.26
     wien
    -1.26
     overla
    -1.21
     effe
    -1.21
     !...
    -1.19
     fep
    -1.19
     milano
    -1.18
    POSITIVE LOGITS
     victory
    0.66
    Abril
    0.60
     win
    0.60
    بالإ
    0.59
    Perd
    0.57
     score
    0.56
    Siga
    0.55
    Glej
    0.55
    AddField
    0.54
    Misión
    0.54
    Activations Density 0.213%

    No Known Activations