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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13911
    Prev
    Next
    INDEX
    Explanations

    password-related security measures and concerns

    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
    876
    +0.14
    0.4%
    1150
    +0.10
    0.3%
    453
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1518
    +0.14
    0.02
    1720
    +0.10
    0.02
    493
    +0.09
    0.03
    Negative Logits
     Rumania
    -0.88
     Mejía
    -0.78
     Marín
    -0.77
     Belén
    -0.72
     Áng
    -0.71
     Khart
    -0.70
     Darío
    -0.70
     Bahía
    -0.69
     Méndez
    -0.68
     Cristóbal
    -0.68
    POSITIVE LOGITS
     password
    0.79
     passphrase
    0.74
     passwords
    0.71
    password
    0.67
     Password
    0.64
     pochette
    0.61
     keyring
    0.60
    Password
    0.55
     mitsubishi
    0.55
     keychain
    0.54
    Activations Density 0.203%

    No Known Activations