© 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. 27039
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "to" indicating purpose or action

    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
    269
    +0.14
    0.8%
    458
    +0.13
    0.7%
    220
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.14
    0.38
    151
    +0.13
    0.31
    434
    +0.13
    0.30
    Negative Logits
    erville
    -1.78
    erc
    -1.56
     filing
    -1.47
    quier
    -1.46
     shoppers
    -1.41
    ely
    -1.40
    ympt
    -1.36
     fate
    -1.33
    urity
    -1.32
    ensch
    -1.31
    POSITIVE LOGITS
    OF
    1.59
    protobuf
    1.45
    ĨĴ
    1.41
    lod
    1.41
    »¿
    1.39
    backed
    1.34
    owned
    1.30
     partly
    1.28
    infl
    1.27
    util
    1.27
    Activations Density 1.639%

    No Known Activations