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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 16244
    Prev
    Next
    INDEX
    Explanations

    texts related to network security and 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
    876
    +0.14
    0.4%
    1842
    +0.13
    0.4%
    511
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.14
    0.04
    1528
    +0.13
    0.03
    1298
    +0.09
    0.02
    Negative Logits
     alkoh
    -0.67
     konserv
    -0.66
     akut
    -0.63
     kosme
    -0.63
     silikon
    -0.62
     Demokrat
    -0.61
     kompres
    -0.61
     akade
    -0.60
     kriminal
    -0.59
     antik
    -0.59
    POSITIVE LOGITS
     smtplib
    0.86
     pylab
    0.77
    /**
    0.71
    <?
    0.67
     skimage
    0.67
     pymysql
    0.66
     vogli
    0.59
    
    0.58
     heapq
    0.57
    Lma
    0.56
    Activations Density 0.266%

    No Known Activations