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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 29725
    Prev
    Next
    INDEX
    Explanations

    references to academic degrees

    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
    500
    +0.13
    0.8%
    358
    +0.12
    0.7%
    89
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    89
    +0.13
    0.03
    500
    +0.12
    0.03
    358
    +0.12
    0.02
    Negative Logits
    ĨĴ
    -2.69
    Ļª
    -1.80
    disambiguation
    -1.77
    ku
    -1.63
     psy
    -1.61
    ³
    -1.58
    Īĺ
    -1.45
     lovely
    -1.43
    Ĥ¬
    -1.42
    woke
    -1.42
    POSITIVE LOGITS
    minded
    1.73
    istry
    1.63
     requirements
    1.57
    wise
    1.55
     matches
    1.55
     considerations
    1.50
     bets
    1.48
     assignment
    1.46
     shots
    1.44
     adaptation
    1.42
    Activations Density 0.015%

    No Known Activations