© 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. 28253
    Prev
    Next
    INDEX
    Explanations

    the use of the word "on" in various contexts

    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
    293
    +0.17
    0.9%
    173
    +0.11
    0.6%
    92
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.17
    0.26
    98
    +0.11
    0.16
    164
    +0.11
    0.20
    Negative Logits
     https
    -1.47
    oid
    -1.45
    ocl
    -1.40
    uding
    -1.40
    ?”
    -1.39
    )\].
    -1.36
    ”?
    -1.35
    \].
    -1.34
     agreeing
    -1.34
    teenth
    -1.33
    POSITIVE LOGITS
    ¿½
    1.74
    thems
    1.73
    ½
    1.67
    ·¸
    1.66
    ĸ´
    1.56
     joy
    1.52
    ¸
    1.49
    Ĭ
    1.48
    irk
    1.48
    ven
    1.47
    Activations Density 3.359%

    No Known Activations