© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 7482
    Prev
    Next
    INDEX
    Explanations

    descriptions of anxiety-inducing situations and strategies for reducing anxiety

    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
    184
    +0.20
    0.6%
    1150
    +0.13
    0.4%
    1577
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.20
    0.03
    736
    +0.13
    0.05
    1499
    +0.11
    0.04
    Negative Logits
     papà
    -0.67
     riviera
    -0.65
     nemico
    -0.65
     Heere
    -0.64
     signore
    -0.64
     Perci
    -0.63
     Epif
    -0.62
     Adieu
    -0.61
     Arro
    -0.61
     vito
    -0.59
    POSITIVE LOGITS
     saad
    0.75
     naer
    0.71
     guma
    0.69
     osal
    0.68
     maksi
    0.64
     mitte
    0.61
     meil
    0.59
     laad
    0.58
     kumar
    0.58
     kuni
    0.58
    Activations Density 0.242%

    No Known Activations