© 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. 29833
    Prev
    Next
    INDEX
    Explanations

    mentions of the United Nations and its associated contexts

    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
    227
    +0.13
    0.7%
    71
    +0.13
    0.7%
    14
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.13
    0.03
    14
    +0.13
    0.03
    375
    +0.12
    0.02
    Negative Logits
    cause
    -1.63
     true
    -1.62
    Middle
    -1.50
     part
    -1.43
    hem
    -1.40
     difference
    -1.35
    backs
    -1.35
     mercy
    -1.34
    eton
    -1.34
    awning
    -1.33
    POSITIVE LOGITS
    ·¸
    1.96
    Īĺ
    1.82
    ĻĤ
    1.80
    ®
    1.73
    µ
    1.64
    ipore
    1.52
     himself
    1.51
    ICO
    1.49
    ·
    1.48
    PLIED
    1.45
    Activations Density 0.024%

    No Known Activations