© 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. 27853
    Prev
    Next
    INDEX
    Explanations

    phrases related to numerical data or measurements

    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
    376
    +0.15
    0.8%
    53
    +0.14
    0.8%
    293
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    293
    +0.15
    0.05
    296
    +0.14
    0.05
    11
    +0.12
    0.05
    Negative Logits
     Parties
    -1.66
    makers
    -1.55
    [_
    -1.50
    ances
    -1.50
    paper
    -1.44
    &-
    -1.43
    orks
    -1.38
    Americans
    -1.35
    prepare
    -1.34
    thems
    -1.33
    POSITIVE LOGITS
    ¾
    2.14
    ¿½
    2.13
    Ī
    2.11
    ¿
    2.08
    Ħ
    2.02
    <|outofrange|>
    2.00
    2.00
    2.00
    2.00
    2.00
    Activations Density 0.023%

    No Known Activations