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. 8244
    Prev
    Next
    INDEX
    Explanations

    phrases related to instructing actions or emphasizing consequences

    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
    1415
    +0.10
    0.3%
    1967
    +0.10
    0.3%
    2019
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1921
    +0.10
    0.05
    1415
    +0.10
    0.03
    1310
    +0.09
    0.03
    Negative Logits
     hairc
    -1.45
     matel
    -1.38
     milf
    -1.38
     !...
    -1.37
     perfet
    -1.36
     Cfr
    -1.34
     milano
    -1.34
     Juf
    -1.32
     ?...
    -1.32
     exé
    -1.32
    POSITIVE LOGITS
     realize
    0.67
     enjoy
    0.67
     look
    0.66
     become
    0.65
     introduce
    0.64
     try
    0.64
     make
    0.64
     tell
    0.63
     say
    0.62
    إذا
    0.62
    Activations Density 0.239%

    No Known Activations