© 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. 16334
    Prev
    Next
    INDEX
    Explanations

    adjectives describing positive characteristics

    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
    478
    +0.16
    0.5%
    776
    +0.13
    0.4%
    50
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1092
    +0.16
    0.05
    16
    +0.13
    0.05
    332
    +0.12
    0.04
    Negative Logits
     malheureux
    -0.75
     pério
    -0.70
     vermelhas
    -0.66
     krep
    -0.64
     naer
    -0.63
     дописавши
    -0.61
     AssemblyProduct
    -0.61
     maksi
    -0.60
    ">/
    -0.59
     haast
    -0.59
    POSITIVE LOGITS
     ability
    0.89
     willingness
    0.75
     inability
    0.71
     tendency
    0.64
     abilities
    0.63
     involvement
    0.61
     monaster
    0.60
    pă
    0.60
     commitment
    0.59
     own
    0.59
    Activations Density 0.237%

    No Known Activations