© 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. 12598
    Prev
    Next
    INDEX
    Explanations

    sentences that express emotions or personal experiences

    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
    2034
    +0.15
    0.5%
    381
    +0.14
    0.5%
    382
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.15
    0.07
    1533
    +0.14
    0.03
    1445
    +0.14
    0.06
    Negative Logits
     increa
    -2.72
     maneu
    -2.61
     impra
    -2.57
     squa
    -2.55
     inev
    -2.55
     fuf
    -2.53
     affor
    -2.53
     reluct
    -2.51
     disagre
    -2.51
     suscep
    -2.50
    POSITIVE LOGITS
     They
    1.10
     There
    1.06
     You
    1.03
     We
    1.03
     It
    1.01
     But
    0.98
     When
    0.96
     One
    0.95
     I
    0.94
     He
    0.94
    Activations Density 0.269%

    No Known Activations