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. 15482
    Prev
    Next
    INDEX
    Explanations

    numerical values related to oil prices and production

    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
    690
    +0.09
    0.3%
    1445
    +0.09
    0.2%
    1343
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    609
    +0.09
    0.04
    382
    +0.09
    0.03
    1513
    +0.08
    0.01
    Negative Logits
     maneu
    -1.75
     encomp
    -1.73
     squa
    -1.72
     fortn
    -1.69
     guarante
    -1.69
     embodi
    -1.69
     desir
    -1.67
     erad
    -1.67
     strick
    -1.66
     fuf
    -1.66
    POSITIVE LOGITS
     price
    0.62
     prices
    0.61
    7
    0.60
    4
    0.60
    5
    0.60
    3
    0.60
    price
    0.59
    2
    0.59
    6
    0.59
    1
    0.58
    Activations Density 0.145%

    No Known Activations