© 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 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. 6361
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative aspects or criticism

    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
    976
    +0.13
    0.5%
    596
    +0.12
    0.4%
    1637
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    976
    +0.13
    0.04
    1637
    +0.12
    0.03
    468
    +0.11
    0.03
    Negative Logits
     unspeak
    -0.79
     ffs
    -0.78
     cuck
    -0.78
     upvoted
    -0.74
     apprehen
    -0.74
     ineffec
    -0.73
     milf
    -0.72
     snoopy
    -0.72
     impra
    -0.71
     increa
    -0.70
    POSITIVE LOGITS
    Bad
    1.09
    bad
    1.09
     bad
    1.05
     Bad
    1.05
     BAD
    0.96
    BAD
    0.94
     baden
    0.67
     boks
    0.64
     syd
    0.62
    sedown
    0.60
    Activations Density 0.077%

    No Known Activations