© 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. 14818
    Prev
    Next
    INDEX
    Explanations

    words related to punditry and expert analysis

    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
    1194
    +0.18
    0.7%
    479
    +0.14
    0.5%
    1350
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1194
    +0.18
    0.06
    1778
    +0.14
    0.05
    75
    +0.13
    0.04
    Negative Logits
     najbol
    -0.59
     maksi
    -0.59
     maraming
    -0.57
     meni
    -0.55
     ilang
    -0.53
     akku
    -0.53
    cheiben
    -0.53
     itong
    -0.53
     šte
    -0.52
     siyang
    -0.52
    POSITIVE LOGITS
     P
    0.67
     p
    0.61
    P
    0.61
     getP
    0.59
    getP
    0.57
    p
    0.53
     pu
    0.52
    ykjav
    0.49
     Pim
    0.48
     pozi
    0.48
    Activations Density 0.581%

    No Known Activations