© 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. 14363
    Prev
    Next
    INDEX
    Explanations

    phrases related to cyber attacks and security breaches

    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
    +0.36
    1.3%
    764
    +0.25
    0.9%
    856
    +0.19
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.36
    0.01
    332
    +0.25
    0.01
    1842
    +0.19
    0.01
    Negative Logits
     impra
    -1.20
     jacques
    -1.16
     shenan
    -1.14
     indestru
    -1.08
     hairc
    -1.03
     disreg
    -1.02
     philanth
    -1.02
     uninten
    -1.01
     embodi
    -1.01
     unspeak
    -1.00
    POSITIVE LOGITS
    IsContent
    1.01
    Personensuche
    0.76
     CreateTagHelper
    0.72
     Vikipedi
    0.72
    TypedDataSet
    0.72
     ModelExpression
    0.71
    RectangleBorder
    0.68
    DoubleQuotes
    0.67
    AddTagHelper
    0.65
    WriteTagHelper
    0.65
    Activations Density 0.032%

    No Known Activations