© 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. 24217
    Prev
    Next
    INDEX
    Explanations

    financial or legal terms related to regulations and compliance

    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
    79
    +0.17
    1.0%
    243
    +0.13
    0.8%
    465
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    376
    +0.17
    0.10
    165
    +0.13
    0.10
    363
    +0.11
    0.07
    Negative Logits
    Ĺ
    -2.26
    Ķ
    -2.07
    ħ
    -2.07
    ļ
    -2.02
    ķ
    -1.95
    ģ
    -1.90
    ı
    -1.85
    ľ
    -1.84
    °
    -1.82
    Ŀ
    -1.81
    POSITIVE LOGITS
    rics
    1.52
    ieurs
    1.48
    ppa
    1.45
    achus
    1.45
     Springer
    1.39
    illac
    1.37
    etta
    1.35
     discs
    1.34
    ÃŃa
    1.33
    ielle
    1.32
    Activations Density 1.656%

    No Known Activations