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. 200
    Prev
    Next
    INDEX
    Explanations

    words related to physical injury and pain

    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
    1842
    +0.19
    0.6%
    2015
    +0.13
    0.4%
    674
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1129
    +0.19
    0.06
    319
    +0.13
    0.04
    184
    +0.11
    0.01
    Negative Logits
     alkoh
    -1.23
     kosme
    -1.15
     silikon
    -1.13
     minimalis
    -1.11
     akut
    -1.02
     optik
    -1.02
     makro
    -0.99
     maksi
    -0.99
     keramik
    -0.96
     kön
    -0.95
    POSITIVE LOGITS
    <bos>
    1.00
    ఏ
    0.51
     lately
    0.50
     tonight
    0.48
    іан
    0.48
     zprá
    0.48
     placental
    0.47
     bezpiecz
    0.46
    pity
    0.46
    cześ
    0.45
    Activations Density 0.620%

    No Known Activations