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. 27366
    Prev
    Next
    INDEX
    Explanations

    the infinitive form of verbs

    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
    197
    +0.12
    0.7%
    51
    +0.12
    0.6%
    343
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.12
    0.04
    109
    +0.12
    0.03
    434
    +0.12
    0.03
    Negative Logits
    IJ
    -2.58
    ı
    -2.04
    ī
    -1.85
    ķ
    -1.84
    ħ
    -1.74
    ¿½
    -1.69
    Ī
    -1.58
     halves
    -1.58
    ↵                                
    -1.56
    ↵    
    -1.56
    POSITIVE LOGITS
    itude
    1.75
    hew
    1.74
     schedule
    1.53
    iculous
    1.51
    javase
    1.50
    7554
    1.43
     hello
    1.43
    ibilities
    1.40
    blog
    1.39
    docs
    1.38
    Activations Density 0.027%

    No Known Activations