Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27306
    Prev
    Next
    INDEX
    Explanations

    concepts that emphasize utility and practicality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    274
    +0.14
    0.8%
    376
    +0.13
    0.7%
    377
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.14
    0.02
    149
    +0.13
    0.01
    267
    +0.11
    0.01
    Negative Logits
    ĨĴ
    -2.99
    Ļª
    -2.87
    ¯
    -2.37
    »¿
    -2.27
    Ĵ
    -2.17
    ·¸
    -2.01
    ķ
    -2.01
    <|outofrange|>
    -1.94
    ↵                 
    -1.94
    ↵                                                                
    -1.94
    POSITIVE LOGITS
    erals
    1.73
     flaw
    1.68
    ities
    1.67
    itat
    1.63
    idade
    1.62
    ibus
    1.61
    wise
    1.56
    idad
    1.56
    imetry
    1.55
    ISPR
    1.51
    Activations Density 0.010%

    No Known Activations