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. 15265
    Prev
    Next
    INDEX
    Explanations

    phrases related to policies, procedures, and governmental actions

    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
    381
    +0.11
    0.4%
    32
    +0.10
    0.3%
    1328
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1590
    +0.11
    0.05
    32
    +0.10
    0.05
    950
    +0.10
    0.05
    Negative Logits
     jaya
    -0.88
     fta
    -0.88
     susun
    -0.83
     hina
    -0.82
     miu
    -0.81
     bayan
    -0.81
     ftre
    -0.81
     bandung
    -0.77
     kasa
    -0.76
     saha
    -0.76
    POSITIVE LOGITS
     no
    0.69
     كومونز
    0.60
     nothing
    0.59
     plenty
    0.57
    UINTN
    0.54
    /**
    0.54
    Theres
    0.50
    no
    0.50
    expandindo
    0.50
     ample
    0.50
    Activations Density 0.139%

    No Known Activations