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. 1541
    Prev
    Next
    INDEX
    Explanations

    phrases related to giving commands or instructions

    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
    1510
    +0.08
    0.2%
    1415
    +0.07
    0.2%
    1978
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1377
    +0.08
    0.03
    1415
    +0.07
    0.03
    1759
    +0.07
    0.04
    Negative Logits
     Traité
    -0.98
     Mémoires
    -0.98
     fta
    -0.98
     hcm
    -0.96
     milf
    -0.95
     Rois
    -0.93
     fte
    -0.92
     fter
    -0.92
     guarante
    -0.92
     „,
    -0.88
    POSITIVE LOGITS
    Havolalar
    0.64
     quit
    0.61
     stop
    0.57
     stay
    0.56
     go
    0.54
     switch
    0.54
     get
    0.54
     مشين
    0.53
     calma
    0.53
    testify
    0.52
    Activations Density 0.321%

    No Known Activations