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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 27229
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or prominent figures

    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
    369
    +0.18
    1.0%
    267
    +0.14
    0.8%
    111
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    267
    +0.18
    0.01
    111
    +0.14
    0.01
    31
    +0.13
    0.01
    Negative Logits
     hers
    -1.86
    ked
    -1.77
    cil
    -1.74
    oint
    -1.70
    Ļª
    -1.67
    atal
    -1.60
    oder
    -1.53
    ĵ
    -1.51
    ternal
    -1.51
    ij
    -1.51
    POSITIVE LOGITS
    anese
    1.64
     efficiencies
    1.62
    icultural
    1.53
    hest
    1.53
    =>
    1.50
     Cycle
    1.48
     =>
    1.44
    idity
    1.43
    ther
    1.43
    igan
    1.39
    Activations Density 0.043%

    No Known Activations