© 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. 26658
    Prev
    Next
    INDEX
    Explanations

    references to arches or arch-related structures

    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
    148
    +0.12
    0.7%
    463
    +0.12
    0.7%
    111
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    117
    +0.12
    0.02
    44
    +0.12
    0.01
    463
    +0.11
    0.01
    Negative Logits
    Ļ
    -3.76
    ı
    -3.49
    §
    -3.32
    ĥ½
    -3.25
    ĵ
    -3.22
    Ķ
    -3.21
    ķ
    -3.19
    ħ
    -3.10
    ľ
    -3.10
    Ħ
    -3.08
    POSITIVE LOGITS
    ived
    1.89
    ways
    1.80
    aic
    1.67
    ipel
    1.65
    bishop
    1.64
     [@
    1.58
     (âī¥
    1.58
     (\>
    1.57
    stones
    1.57
    way
    1.56
    Activations Density 0.005%

    No Known Activations