© 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 EvalsExportsinterp-engineNEWAPI 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. 14912
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical skills, education, and training

    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
    1984
    +0.13
    0.4%
    860
    +0.11
    0.3%
    1403
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1984
    +0.13
    0.04
    860
    +0.11
    0.04
    921
    +0.09
    0.03
    Negative Logits
     Hitam
    -0.74
     Kategor
    -0.71
     frambo
    -0.71
     jawa
    -0.67
     papà
    -0.67
     jaya
    -0.67
    moiselle
    -0.67
     bambou
    -0.66
     héro
    -0.66
     maske
    -0.66
    POSITIVE LOGITS
    Sebagai
    0.90
     result
    0.84
     consequence
    0.77
    Și
    0.71
    sebagai
    0.68
    Jako
    0.66
     reminder
    0.63
    result
    0.60
    Dacă
    0.59
    Gdy
    0.58
    Activations Density 0.096%

    No Known Activations