© 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. 30236
    Prev
    Next
    INDEX
    Explanations

    frequent references to "the" and indications of work-related themes

    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
    285
    +0.15
    0.9%
    56
    +0.12
    0.7%
    436
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.15
    0.42
    23
    +0.12
    0.38
    98
    +0.10
    0.18
    Negative Logits
     length
    -1.70
     purpose
    -1.65
     width
    -1.56
    icals
    -1.53
    documentclass
    -1.50
    xiety
    -1.45
    stones
    -1.41
    rics
    -1.41
     existing
    -1.40
     literature
    -1.38
    POSITIVE LOGITS
    apat
    1.96
    heta
    1.79
    arte
    1.55
    ANC
    1.49
    :--
    1.45
     initiation
    1.43
     specimen
    1.41
    illance
    1.40
    stra
    1.40
    ari
    1.36
    Activations Density 4.512%

    No Known Activations