© 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. 4715
    Prev
    Next
    INDEX
    Explanations

    phrases related to attracting or gaining attention or interest

    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
    1482
    +0.14
    0.5%
    1038
    +0.13
    0.4%
    25
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1038
    +0.14
    0.03
    1482
    +0.13
    0.03
    1140
    +0.12
    0.03
    Negative Logits
    Synonymes
    -0.47
    PCell
    -0.46
    TypedValue
    -0.44
    المناصب
    -0.44
    Da
    -0.43
    нутрен
    -0.43
     NSError
    -0.42
     октября
    -0.42
    wieś
    -0.42
    País
    -0.42
    POSITIVE LOGITS
     attract
    1.13
     attracts
    1.08
     attraction
    1.07
     attracting
    1.06
     Attraction
    1.04
     attracted
    1.04
     Attra
    1.03
    Attra
    0.94
    attra
    0.91
    attraction
    0.84
    Activations Density 0.086%

    No Known Activations