© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 13562
    Prev
    Next
    INDEX
    Explanations

    words related to trauma and incidents of trauma

    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
    1233
    +0.15
    0.5%
    1896
    +0.12
    0.4%
    1296
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1233
    +0.15
    0.02
    468
    +0.12
    0.02
    1363
    +0.12
    0.01
    Negative Logits
     Kön
    -0.70
     disreg
    -0.69
     divisi
    -0.60
     apparente
    -0.59
     Solidar
    -0.58
     Biele
    -0.58
     dilap
    -0.58
     karte
    -0.58
     ritard
    -0.58
     zara
    -0.58
    POSITIVE LOGITS
     trauma
    1.34
     Trauma
    1.22
    Trauma
    1.19
     traum
    1.03
    traumatic
    0.98
     traumatic
    0.98
    trauma
    0.97
     traumas
    0.91
    traum
    0.80
     Traumatic
    0.69
    Activations Density 0.064%

    No Known Activations