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. 15561
    Prev
    Next
    INDEX
    Explanations

    occurrences of the preposition "at"

    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
    1323
    +0.13
    0.5%
    1974
    +0.13
    0.4%
    1984
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1323
    +0.13
    0.04
    1974
    +0.13
    0.04
    395
    +0.12
    0.05
    Negative Logits
     Sequo
    -0.58
    rictions
    -0.57
    iented
    -0.57
    épendant
    -0.56
    othesis
    -0.55
    hæng
    -0.54
    épendance
    -0.53
     tanong
    -0.52
    orical
    -0.51
    idance
    -0.50
    POSITIVE LOGITS
    At
    0.89
    at
    0.88
     At
    0.84
     AT
    0.79
     at
    0.72
    AT
    0.69
    Least
    0.67
     dirait
    0.66
    Automat
    0.65
     croit
    0.64
    Activations Density 0.125%

    No Known Activations