© 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. 27138
    Prev
    Next
    INDEX
    Explanations

    repeated iterations through collections, specifically using the "foreach" construct

    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
    44
    +0.13
    0.7%
    117
    +0.12
    0.7%
    193
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    44
    +0.13
    0.02
    117
    +0.12
    0.01
    193
    +0.11
    0.01
    Negative Logits
    ĥ
    -2.00
    ĩ
    -1.74
    ĥ½
    -1.69
    ħ
    -1.67
    hores
    -1.53
    ģ
    -1.48
    hs
    -1.43
    pite
    -1.43
    ĵ
    -1.41
    hers
    -1.41
    POSITIVE LOGITS
    room
    1.93
    sector
    1.68
    ophone
    1.67
    anguage
    1.64
     aisle
    1.64
    êt
    1.63
    thouse
    1.62
    geb
    1.62
    lane
    1.61
    wiki
    1.59
    Activations Density 0.197%

    No Known Activations