© 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. 22428
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and references to personal identity

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    256
    +0.12
    0.7%
    91
    +0.12
    0.7%
    15
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.12
    0.06
    492
    +0.12
    0.07
    170
    +0.11
    0.06
    Negative Logits
    obal
    -1.67
    aca
    -1.47
    ifs
    -1.44
    ities
    -1.43
    ah
    -1.38
    afa
    -1.37
     news
    -1.37
    quote
    -1.36
    fo
    -1.34
    bee
    -1.33
    POSITIVE LOGITS
    Ļ
    3.52
    ´
    3.14
    ĥ
    2.98
    ¼
    2.97
    ĥ½
    2.97
    ↵
    2.96
    2.96
             ↵
    2.96
    ↵
    2.96
    <|outofrange|>
    2.96
    Activations Density 0.627%

    No Known Activations