© 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 EvalsExportsAPI 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. 5705
    Prev
    Next
    INDEX
    Explanations

    outpouring of emotions and condolences related to a tragic event or loss

    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
    1533
    +0.11
    0.3%
    332
    +0.08
    0.2%
    478
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1355
    +0.11
    0.03
    1533
    +0.08
    0.01
    1957
    +0.08
    0.02
    Negative Logits
     AGRIC
    -0.69
     devaient
    -0.65
     faisaient
    -0.63
     jati
    -0.60
     ABBRE
    -0.58
     [''
    -0.56
     impractica
    -0.55
     lamella
    -0.54
     firent
    -0.54
     Standardi
    -0.53
    POSITIVE LOGITS
    <bos>
    0.88
     loved
    0.65
     Cataluña
    0.56
     always
    0.55
     predeceased
    0.55
    always
    0.53
    tisseur
    0.52
     Loved
    0.52
     Siria
    0.51
     adored
    0.51
    Activations Density 0.265%

    No Known Activations