© 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. 3318
    Prev
    Next
    INDEX
    Explanations

    words related to passwords and security vulnerabilities

    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
    1044
    +0.14
    0.5%
    204
    +0.14
    0.5%
    645
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1044
    +0.14
    0.02
    204
    +0.14
    0.02
    1601
    +0.11
    0.02
    Negative Logits
     shenan
    -0.92
     accla
    -0.89
     apprehen
    -0.83
     inev
    -0.82
     disagre
    -0.79
     unspeak
    -0.79
     intersper
    -0.79
     reluct
    -0.78
     increa
    -0.78
     racon
    -0.77
    POSITIVE LOGITS
     password
    1.49
    password
    1.33
     Password
    1.30
     passwords
    1.30
    Password
    1.21
    PASSWORD
    1.15
    getPassword
    1.13
    setPassword
    1.11
     PASSWORD
    1.01
     getPassword
    0.98
    Activations Density 0.066%

    No Known Activations