© 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. 14741
    Prev
    Next
    INDEX
    Explanations

    emotional and personal narrative content, particularly focusing on loss and deep relationships

    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
    674
    +0.15
    0.5%
    468
    +0.14
    0.4%
    1937
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    972
    +0.15
    0.06
    1937
    +0.14
    0.07
    468
    +0.10
    0.06
    Negative Logits
     İl
    -0.46
    Ī
    -0.45
    Therefore
    -0.45
     الاطلاع
    -0.45
     Hence
    -0.44
    pushd
    -0.43
    Std
    -0.43
    However
    -0.42
    FontOfSize
    -0.42
    Hence
    -0.41
    POSITIVE LOGITS
     affez
    0.82
     dags
    0.76
     germain
    0.76
     tyme
    0.75
     reft
    0.74
     vivace
    0.72
     naer
    0.72
     marrone
    0.70
     eccellente
    0.69
     rispond
    0.68
    Activations Density 0.419%

    No Known Activations