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. 15903
    Prev
    Next
    INDEX
    Explanations

    numbers with a particular structure

    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
    1553
    +0.09
    0.3%
    1499
    +0.09
    0.3%
    1882
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.09
    0.04
    1882
    +0.09
    0.04
    330
    +0.08
    0.03
    Negative Logits
     unden
    -1.11
     indestru
    -1.11
     madonna
    -1.11
     inext
    -1.09
     hentai
    -1.08
     affor
    -1.06
     wattpad
    -1.05
     snoopy
    -1.05
     hairc
    -1.04
     deleter
    -1.03
    POSITIVE LOGITS
     kasarigan
    0.62
     inflation
    0.62
     liquidity
    0.50
    inflation
    0.50
     policy
    0.48
    Географиясе
    0.47
    WebVitals
    0.46
     hikes
    0.46
     rate
    0.46
    Gweler
    0.45
    Activations Density 0.238%

    No Known Activations