© 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. 13232
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal opinions or thoughts

    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
    1757
    +0.19
    0.7%
    605
    +0.15
    0.5%
    478
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1757
    +0.19
    0.06
    1141
    +0.15
    0.04
    976
    +0.12
    0.05
    Negative Logits
     maksi
    -1.21
     ?...
    -1.17
     erik
    -1.12
     🤣🤣
    -1.12
     purcha
    -1.07
     reluct
    -1.06
     !...
    -1.06
     antik
    -1.06
     depic
    -1.05
     milf
    -1.04
    POSITIVE LOGITS
     really
    1.06
    really
    0.99
    Really
    0.91
     Really
    0.89
     REALLY
    0.89
     wirklich
    0.70
    <bos>
    0.69
     realmente
    0.65
     truly
    0.64
     naprawdę
    0.58
    Activations Density 0.083%

    No Known Activations