Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15146
    Prev
    Next
    INDEX
    Explanations

    words related to accidents, injuries, and emergencies

    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
    1216
    +0.07
    0.2%
    674
    +0.07
    0.2%
    630
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.07
    0.04
    1493
    +0.07
    0.02
    736
    +0.07
    0.04
    Negative Logits
     unie
    -0.55
    jws
    -0.53
    webElementGuid
    -0.51
     rente
    -0.50
     Dokter
    -0.49
    petito
    -0.49
    FFIX
    -0.48
     spis
    -0.47
    CopyWith
    -0.47
     corrom
    -0.47
    POSITIVE LOGITS
     newArr
    0.86
     jorge
    0.81
     ftu
    0.80
     pymongo
    0.78
     sergio
    0.75
     yves
    0.73
     pymysql
    0.70
     Lmao
    0.70
     pylab
    0.69
     roberto
    0.69
    Activations Density 0.186%

    No Known Activations