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. 15317
    Prev
    Next
    INDEX
    Explanations

    people describing their background and experiences

    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
    227
    +0.10
    0.3%
    1741
    +0.09
    0.3%
    845
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    658
    +0.10
    0.06
    1692
    +0.09
    0.03
    1727
    +0.09
    0.03
    Negative Logits
    jandro
    -0.55
     malheureux
    -0.50
    stasia
    -0.50
    )>=
    -0.48
    heran
    -0.47
     berken
    -0.47
    eckel
    -0.46
     makam
    -0.46
    ikyuu
    -0.46
    侵略
    -0.46
    POSITIVE LOGITS
     myself
    0.74
    Sebagai
    0.64
    <bos>
    0.62
    GEBURTSDATUM
    0.61
    Setiap
    0.60
    Bukan
    0.59
    álbum
    0.58
    expandindo
    0.56
    фициальный
    0.56
    Sklici
    0.56
    Activations Density 0.550%

    No Known Activations