© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 27783
    Prev
    Next
    INDEX
    Explanations

    references to sheets, particularly in the context of bedding or laundry

    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
    376
    +0.17
    1.0%
    156
    +0.15
    0.9%
    306
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    306
    +0.17
    0.01
    19
    +0.15
    0.01
    198
    +0.13
    0.01
    Negative Logits
     yours
    -2.14
     choosing
    -1.74
     vain
    -1.68
     somebody
    -1.61
    rian
    -1.58
     fancy
    -1.53
     your
    -1.52
     groups
    -1.50
     Walt
    -1.49
     dreams
    -1.48
    POSITIVE LOGITS
    ĻĤ
    2.30
    ģ
    2.26
    80211
    1.95
    ball
    1.91
    dimen
    1.82
    uve
    1.81
    Ī
    1.77
    iom
    1.77
    eto
    1.76
    heet
    1.72
    Activations Density 0.014%

    No Known Activations