© 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. 28161
    Prev
    Next
    INDEX
    Explanations

    superscript formatting in text

    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
    46
    +0.16
    0.9%
    164
    +0.13
    0.7%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    46
    +0.16
    0.01
    40
    +0.13
    0.01
    273
    +0.11
    0.01
    Negative Logits
     knees
    -1.89
    ¿
    -1.79
     dignity
    -1.62
    ķ
    -1.56
    nez
    -1.55
    fulness
    -1.54
    ikh
    -1.52
    ŀ
    -1.45
    ingale
    -1.44
    zos
    -1.41
    POSITIVE LOGITS
    onents
    1.73
    inator
    1.66
    onent
    1.65
    pective
    1.60
    ensa
    1.53
    otyping
    1.49
    ardi
    1.47
    ilation
    1.47
    otyp
    1.42
    ulsive
    1.39
    Activations Density 0.006%

    No Known Activations