© 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. 5252
    Prev
    Next
    INDEX
    Explanations

    explanations or reasoning about a situation or character's behavior

    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
    674
    +0.09
    0.2%
    62
    +0.08
    0.2%
    964
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1543
    +0.09
    0.03
    310
    +0.08
    0.02
    269
    +0.07
    0.03
    Negative Logits
    protoc
    -0.65
     Singapur
    -0.62
     maksi
    -0.59
    "}")
    -0.57
     kasar
    -0.57
     minera
    -0.56
     teras
    -0.56
     foton
    -0.56
     makro
    -0.55
     alkoh
    -0.52
    POSITIVE LOGITS
     scrat
    1.08
     suscep
    1.07
     unden
    1.07
     disreg
    1.03
     accla
    1.01
     perfet
    1.00
     increa
    0.99
     indestru
    0.99
     embodi
    0.98
     inext
    0.97
    Activations Density 0.222%

    No Known Activations