© 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. 29831
    Prev
    Next
    INDEX
    Explanations

    the concept of sustainability in various contexts

    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
    376
    +0.18
    1.0%
    115
    +0.17
    1.0%
    11
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    11
    +0.18
    0.01
    419
    +0.17
    0.01
    451
    +0.12
    0.01
    Negative Logits
    defer
    -1.61
     Delaware
    -1.55
    *\*
    -1.53
     Maryland
    -1.45
    eps
    -1.43
    lickr
    -1.41
    akia
    -1.41
    inian
    -1.41
    IRS
    -1.38
    IFF
    -1.38
    POSITIVE LOGITS
    Ł
    2.80
    ľĵ
    2.64
    ļ
    2.49
    ¢
    2.31
    ŀ
    2.31
    ¾
    2.27
    ¨
    2.25
    ł
    2.20
    Ļ
    2.18
    °
    2.17
    Activations Density 0.017%

    No Known Activations