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. 8310
    Prev
    Next
    INDEX
    Explanations

    dialogue lines enclosed in quotation marks

    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
    674
    +0.45
    3.1%
    108
    +0.07
    0.5%
    1741
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1403
    +0.45
    0.22
    800
    +0.07
    0.26
    15
    +0.07
    0.24
    Negative Logits
     reluct
    -3.79
     unspeak
    -3.79
     impra
    -3.71
     shenan
    -3.66
     disgra
    -3.59
     indestru
    -3.58
     disreg
    -3.54
     disagre
    -3.51
     increa
    -3.49
     inconce
    -3.42
    POSITIVE LOGITS
    <bos>
    13.70
    Autoritní
    2.44
     betweenstory
    2.40
    GEBURTSDATUM
    2.34
    expandindo
    2.30
    تقاوى
    2.13
     Paglinawan
    2.11
     Administrativna
    2.08
     autorytatywna
    2.08
     Italijani
    2.07
    Activations Density 0.084%

    No Known Activations