© 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. 2-MLP-SM
    11. 25500
    Prev
    Next
    INDEX
    Explanations

    references to terms and conditions

    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
    83
    +0.12
    0.7%
    322
    +0.11
    0.6%
    163
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    322
    +0.12
    0.01
    163
    +0.11
    0.01
    55
    +0.11
    0.02
    Negative Logits
    iph
    -1.63
    board
    -1.44
    ante
    -1.41
    reed
    -1.38
    ended
    -1.36
     awaited
    -1.36
    endar
    -1.35
    publ
    -1.34
     record
    -1.33
    mem
    -1.32
    POSITIVE LOGITS
    §
    2.13
    Ń
    2.02
    ¼
    1.88
    Ĺ
    1.86
    ³
    1.80
    ļ
    1.77
    »
    1.69
    µ
    1.67
    ¨
    1.66
    :</
    1.63
    Activations Density 0.053%

    No Known Activations