© 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. 27032
    Prev
    Next
    INDEX
    Explanations

    words or phrases that indicate detailed explanations or descriptions

    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
    156
    +0.18
    1.1%
    436
    +0.14
    0.8%
    376
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    436
    +0.18
    0.01
    401
    +0.14
    0.01
    505
    +0.14
    0.01
    Negative Logits
     hers
    -1.70
    astern
    -1.60
     possible
    -1.53
    avir
    -1.52
    OOGLE
    -1.48
    anges
    -1.46
    angers
    -1.45
    ____________
    -1.42
    ever
    -1.42
    owed
    -1.40
    POSITIVE LOGITS
    ¢
    3.99
    ģ
    3.50
    £
    3.39
    Īĺ
    3.25
    ł
    3.15
    ±
    3.15
    ¡
    3.02
    ¿½
    2.93
    »¿
    2.88
    ĸ
    2.86
    Activations Density 0.010%

    No Known Activations