© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 28258
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "ek"

    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
    211
    +0.12
    0.7%
    434
    +0.12
    0.7%
    450
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    211
    +0.12
    0.02
    450
    +0.12
    0.02
    64
    +0.11
    0.02
    Negative Logits
     sexes
    -1.74
     ?"
    -1.70
    ONS
    -1.66
     FILE
    -1.63
    >`
    -1.61
     Tobacco
    -1.60
    ~*
    -1.55
    zzles
    -1.51
    usterity
    -1.49
    ances
    -1.49
    POSITIVE LOGITS
    ĻĤ
    2.91
    ĩ
    2.69
    ↵  
    2.53
                                                      
    2.53
    <|outofrange|>
    2.53
                  ↵ 
    2.53
    ↵  âĢĥ
    2.53
    č↵                       
    2.53
    ↵        ↵       
    2.53
    <|outofrange|>
    2.53
    Activations Density 0.040%

    No Known Activations