© 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. 30428
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving square roots

    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
    164
    +0.16
    0.9%
    111
    +0.13
    0.8%
    382
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.16
    0.01
    111
    +0.13
    0.01
    482
    +0.12
    0.01
    Negative Logits
    Ģ
    -2.09
    º
    -1.82
    OVA
    -1.65
    ´
    -1.57
    nez
    -1.53
     miss
    -1.51
    ĭ
    -1.51
    ¾
    -1.51
     LORD
    -1.50
    ATES
    -1.41
    POSITIVE LOGITS
    igent
    1.71
    imet
    1.60
    idone
    1.56
    vous
    1.55
    idor
    1.49
    bugs
    1.45
    ings
    1.44
     kinases
    1.43
    markets
    1.42
    olved
    1.40
    Activations Density 0.051%

    No Known Activations