© 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. 24277
    Prev
    Next
    INDEX
    Explanations

    references to relationships or connections

    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
    156
    +0.18
    1.0%
    353
    +0.13
    0.7%
    447
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    349
    +0.18
    0.05
    313
    +0.13
    0.02
    267
    +0.12
    0.04
    Negative Logits
    idable
    -1.59
    ocene
    -1.57
    axon
    -1.55
    seys
    -1.53
    bic
    -1.49
    wid
    -1.46
    že
    -1.46
    agma
    -1.41
     tight
    -1.40
    icol
    -1.40
    POSITIVE LOGITS
     processors
    1.41
     old
    1.39
     workers
    1.36
     remark
    1.34
     propagate
    1.33
     friends
    1.32
     Duty
    1.32
     authorities
    1.29
     servers
    1.29
    gard
    1.29
    Activations Density 0.375%

    No Known Activations