© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 22716
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'anyone' in various contexts

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    6
    +0.10
    0.7%
    271
    +0.09
    0.7%
    190
    +0.08
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    357
    +0.10
    0.02
    185
    +0.09
    0.02
    138
    +0.08
    0.02
    Negative Logits
    cknowled
    -1.24
     Ricci
    -1.24
     everyone
    -1.17
     Einstein
    -1.16
     Holder
    -1.14
    witz
    -1.11
     Franco
    -1.10
     Cook
    -1.10
     grub
    -1.09
     Operating
    -1.08
    POSITIVE LOGITS
    Ļ
    4.13
    ®
    4.09
    Ľ
    3.98
    ĥ
    3.92
    ĥ½
    3.88
    ½
    3.86
    ¾
    3.73
    £
    3.72
             ↵
    3.71
    <|outofrange|>
    3.71
    Activations Density 0.016%

    No Known Activations