© 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. 26952
    Prev
    Next
    INDEX
    Explanations

    words related to orphanhood or abandonment

    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
    71
    +0.10
    0.6%
    148
    +0.10
    0.6%
    339
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    13
    +0.10
    0.01
    200
    +0.10
    0.01
    339
    +0.10
    0.01
    Negative Logits
    '?"
    -1.69
    "?"
    -1.65
    ?'
    -1.64
    ...?"
    -1.53
    ...'
    -1.50
     particular
    -1.49
     ?"
    -1.48
    pton
    -1.47
     previous
    -1.46
     latter
    -1.41
    POSITIVE LOGITS
    seud
    1.94
    gap
    1.64
    ibase
    1.64
    album
    1.60
    cias
    1.58
    som
    1.53
    stock
    1.52
    ĻĤ
    1.51
    rams
    1.51
    ↵³³
    1.42
    Activations Density 1.645%

    No Known Activations