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. 2986
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and possessive determiners

    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
    1385
    +0.11
    0.3%
    478
    +0.11
    0.3%
    942
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    303
    +0.11
    0.04
    397
    +0.11
    0.03
    478
    +0.09
    0.04
    Negative Logits
     maneu
    -1.34
     accla
    -1.32
     desir
    -1.29
     laun
    -1.28
     depic
    -1.28
     effe
    -1.28
     secon
    -1.26
     wien
    -1.25
     fuf
    -1.25
     fortn
    -1.24
    POSITIVE LOGITS
    <bos>
    0.97
     teachings
    0.64
     kindness
    0.63
     latest
    0.61
     generosity
    0.59
     guidance
    0.59
    s
    0.58
     words
    0.57
     advice
    0.56
     approval
    0.56
    Activations Density 0.270%

    No Known Activations