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. 27613
    Prev
    Next
    INDEX
    Explanations

    occurrences of data type declarations for character variables

    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
    254
    +0.16
    0.9%
    232
    +0.15
    0.8%
    74
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    254
    +0.16
    0.03
    232
    +0.15
    0.03
    373
    +0.13
    0.02
    Negative Logits
    ³
    -2.03
    ´
    -1.94
    į
    -1.60
    ↵			
    -1.53
     vicinity
    -1.49
     same
    -1.49
    pping
    -1.42
    Ħ
    -1.38
    Ĭ
    -1.37
    IJ
    -1.36
    POSITIVE LOGITS
    nel
    1.84
    vie
    1.81
    zol
    1.78
    istically
    1.71
    acters
    1.70
    vin
    1.67
    gage
    1.67
    nett
    1.64
    bag
    1.64
    thouse
    1.64
    Activations Density 0.012%

    No Known Activations