© 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. 25741
    Prev
    Next
    INDEX
    Explanations

    possessive contractions or forms

    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
    69
    +0.12
    0.7%
    260
    +0.11
    0.6%
    364
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    380
    +0.12
    0.02
    470
    +0.11
    0.03
    364
    +0.11
    0.03
    Negative Logits
    ¼
    -1.96
    Īĺ
    -1.75
    ¬
    -1.73
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -1.66
     regards
    -1.65
     combination
    -1.65
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -1.64
    <|outofrange|>
    -1.63
    ↵↵
    -1.63
     ↵
    -1.63
    POSITIVE LOGITS
    idase
    1.78
    ylase
    1.76
    itis
    1.74
    onen
    1.71
    ance
    1.64
    hin
    1.64
    anda
    1.58
    ality
    1.58
    nai
    1.56
    zech
    1.55
    Activations Density 0.166%

    No Known Activations