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. 8315
    Prev
    Next
    INDEX
    Explanations

    personal pronouns referring to a specific individual

    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
    1978
    +0.17
    0.5%
    381
    +0.16
    0.5%
    1919
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.17
    0.09
    1510
    +0.16
    0.06
    1637
    +0.15
    0.05
    Negative Logits
     olx
    -1.24
     levis
    -1.22
     budapest
    -1.19
     fatis
    -1.18
     magis
    -1.16
     umo
    -1.16
     Juf
    -1.14
     tanong
    -1.14
     wien
    -1.13
     lele
    -1.12
    POSITIVE LOGITS
    He
    0.87
     He
    0.86
     he
    0.85
    he
    0.77
     didn
    0.75
     himself
    0.74
     did
    0.72
    She
    0.71
     hasn
    0.70
     She
    0.69
    Activations Density 0.282%

    No Known Activations