© 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 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. 28911
    Prev
    Next
    INDEX
    Explanations

    instances of HTML elements and tags in the text

    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
    460
    +0.13
    0.7%
    71
    +0.13
    0.7%
    238
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    460
    +0.13
    0.02
    341
    +0.13
    0.01
    55
    +0.11
    0.01
    Negative Logits
     your
    -1.59
     yours
    -1.58
    atively
    -1.43
     Ubuntu
    -1.42
     Microsoft
    -1.38
     Python
    -1.35
     ?"
    -1.34
     progress
    -1.33
     Jess
    -1.33
     away
    -1.33
    POSITIVE LOGITS
    fors
    1.66
    âĢIJ
    1.62
    LETE
    1.57
    bag
    1.54
    ious
    1.51
    Script
    1.47
    fruit
    1.47
    edo
    1.46
     likes
    1.43
    headed
    1.42
    Activations Density 0.009%

    No Known Activations