© 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. 2-MLP-SM
    11. 24084
    Prev
    Next
    INDEX
    Explanations

    references to leadership roles and positions of authority

    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
    156
    +0.17
    1.0%
    511
    +0.12
    0.7%
    334
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    177
    +0.17
    0.02
    334
    +0.12
    0.03
    479
    +0.12
    0.01
    Negative Logits
    Ľ
    -2.74
    ĸ
    -2.70
    ĵ
    -2.65
    Ĵ
    -2.61
    º
    -2.54
    Ļ
    -2.49
    £
    -2.49
    ¾
    -2.49
    ®
    -2.49
    ©
    -2.41
    POSITIVE LOGITS
    ounding
    1.56
    amen
    1.55
    ship
    1.49
     yourself
    1.48
    agging
    1.46
     office
    1.45
    ational
    1.44
     abdomen
    1.43
    estine
    1.43
     myself
    1.39
    Activations Density 0.262%

    No Known Activations