© 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. 4705
    Prev
    Next
    INDEX
    Explanations

    words related to chemical processes and equipment

    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
    876
    +0.15
    0.5%
    736
    +0.15
    0.5%
    1385
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.15
    0.08
    724
    +0.15
    0.04
    1385
    +0.15
    0.04
    Negative Logits
     bascul
    -0.88
     verhe
    -0.72
     wortel
    -0.71
     praktik
    -0.70
     Zoltán
    -0.69
     kooper
    -0.69
     philanth
    -0.67
     optik
    -0.66
     parteci
    -0.66
     meras
    -0.65
    POSITIVE LOGITS
     debris
    0.73
     particles
    0.69
     residue
    0.66
     impurities
    0.64
     residual
    0.64
     residues
    0.64
     kasama
    0.63
     EoL
    0.61
     makita
    0.60
     contaminants
    0.60
    Activations Density 0.366%

    No Known Activations