© 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. 29259
    Prev
    Next
    INDEX
    Explanations

    references to compressed file formats, specifically gzip and tar.gz

    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
    264
    +0.12
    0.7%
    286
    +0.10
    0.6%
    397
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    264
    +0.12
    0.01
    286
    +0.10
    0.01
    397
    +0.10
    0.01
    Negative Logits
    Ĥ
    -2.10
    ¿½
    -2.10
    ĵ
    -2.08
    Ĩ
    -2.06
    ¦
    -2.02
    Īĺ
    -1.96
    ı
    -1.89
    Ĥ¬
    -1.86
    ´
    -1.86
    ĭ
    -1.84
    POSITIVE LOGITS
    ÅĽci
    2.09
    eries
    1.84
    esan
    1.76
     Rptr
    1.70
    ün
    1.66
    rooms
    1.60
    illion
    1.60
    ee
    1.58
    room
    1.57
    opan
    1.56
    Activations Density 0.059%

    No Known Activations