© 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. 5201
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms related to animals and medical conditions, especially focusing on a controversial theory regarding how a particular animal kills its prey

    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
    1331
    +0.14
    0.5%
    204
    +0.12
    0.4%
    555
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.14
    0.06
    1331
    +0.12
    0.04
    1575
    +0.12
    0.04
    Negative Logits
     mieszkań
    -0.49
     '+':
    -0.47
    copyOf
    -0.47
     С
    -0.47
     odc
    -0.47
     działal
    -0.47
    Beruf
    -0.47
     maging
    -0.46
     c
    -0.46
    填充
    -0.45
    POSITIVE LOGITS
     Mlle
    1.32
     Sén
    1.27
     Mémoires
    1.21
     applau
    1.20
     Chapitre
    1.19
     embra
    1.16
     Châ
    1.14
    tldr
    1.13
     simplif
    1.12
     aquarelle
    1.11
    Activations Density 0.173%

    No Known Activations