© 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. 0-MLP-SM
    11. 25083
    Prev
    Next
    INDEX
    Explanations

    repeated requests or prompts for action

    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/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
    Neuron Alignment
    Index
    Value
    % of L₁
    0
    +0.14
    0.8%
    494
    +0.14
    0.8%
    376
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    +0.14
    0.04
    341
    +0.14
    0.03
    235
    +0.13
    0.03
    Negative Logits
    ·
    -2.62
    Ĥ
    -2.32
    ĻĤ
    -2.09
    ¸
    -2.08
    ¹
    -1.95
    Ĵ
    -1.95
    ŀ
    -1.93
    Ķ
    -1.92
    ·¸
    -1.91
    ³
    -1.88
    POSITIVE LOGITS
    gery
    1.63
     wa
    1.60
     tone
    1.53
    ?_
    1.47
     preg
    1.47
     park
    1.41
     pleading
    1.40
     forgive
    1.39
    cox
    1.39
     jer
    1.38
    Activations Density 0.016%

    No Known Activations