© 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. 13210
    Prev
    Next
    INDEX
    Explanations

    phrases expressing strong opinions or stances

    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
    599
    +0.11
    0.3%
    766
    +0.10
    0.3%
    1919
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    599
    +0.11
    0.06
    1919
    +0.10
    0.06
    862
    +0.08
    0.03
    Negative Logits
     hcm
    -0.99
     palab
    -0.98
     siena
    -0.94
     thut
    -0.93
     vne
    -0.93
     santiago
    -0.93
     fatis
    -0.92
     nomine
    -0.92
     parati
    -0.91
     milano
    -0.90
    POSITIVE LOGITS
     ostavi
    0.56
     trust
    0.53
    viewing
    0.51
     watching
    0.50
     understand
    0.48
     expect
    0.48
     internetowa
    0.47
    ometrial
    0.47
     demand
    0.46
     understanding
    0.46
    Activations Density 0.402%

    No Known Activations