© 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. 27830
    Prev
    Next
    INDEX
    Explanations

    references to companies or entities in the context of industries or sectors

    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
    +0.20
    1.1%
    75
    +0.14
    0.8%
    81
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.20
    0.02
    301
    +0.14
    0.02
    71
    +0.13
    0.02
    Negative Logits
    backs
    -1.64
    vers
    -1.63
     bat
    -1.60
    amycin
    -1.56
    woke
    -1.47
    itrile
    -1.45
     listening
    -1.43
     listener
    -1.41
    ades
    -1.37
    ids
    -1.37
    POSITIVE LOGITS
    Bank
    2.06
     Ltd
    1.86
    ystem
    1.85
     Corporation
    1.83
    bank
    1.74
     Federation
    1.73
    naire
    1.67
     Limited
    1.64
    plan
    1.64
    ystems
    1.63
    Activations Density 0.044%

    No Known Activations