© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27120
    Prev
    Next
    INDEX
    Explanations

    instances of the word "themselves."

    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
    376
    +0.16
    0.9%
    353
    +0.12
    0.7%
    85
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    353
    +0.16
    0.04
    384
    +0.12
    0.03
    441
    +0.11
    0.03
    Negative Logits
    rap
    -1.73
    cept
    -1.64
     condition
    -1.59
     herself
    -1.53
     her
    -1.43
     grade
    -1.42
    backs
    -1.40
    etime
    -1.37
    night
    -1.34
    quired
    -1.32
    POSITIVE LOGITS
     CURIAM
    1.75
    atic
    1.66
    CUIT
    1.56
    nal
    1.55
    chitz
    1.54
    emente
    1.47
    acters
    1.42
    adow
    1.42
    adows
    1.40
    atically
    1.39
    Activations Density 0.439%

    No Known Activations