© 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. 27994
    Prev
    Next
    INDEX
    Explanations

    phrases indicating excessive resource usage or allocation

    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
    282
    +0.15
    0.9%
    266
    +0.12
    0.7%
    362
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    282
    +0.15
    0.09
    266
    +0.12
    0.07
    7
    +0.11
    0.07
    Negative Logits
     eye
    -1.78
    UAL
    -1.56
    unal
    -1.50
     bladder
    -1.49
    IR
    -1.48
    EC
    -1.47
    antly
    -1.42
    icul
    -1.36
    ricular
    -1.36
    less
    -1.36
    POSITIVE LOGITS
    loaded
    1.81
    arching
    1.67
    kill
    1.67
    came
    1.62
    µ
    1.60
    wrote
    1.58
    powered
    1.55
    statement
    1.54
    ł
    1.51
    hang
    1.45
    Activations Density 0.318%

    No Known Activations