© 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. 26866
    Prev
    Next
    INDEX
    Explanations

    instances of the word "comply" and its variations

    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
    156
    +0.21
    1.2%
    376
    +0.17
    1.0%
    232
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.21
    0.01
    46
    +0.17
    0.01
    167
    +0.11
    0.01
    Negative Logits
    hire
    -1.78
    /~
    -1.52
    ){#
    -1.42
    OLOG
    -1.40
    ____________
    -1.39
     commitment
    -1.39
    Biography
    -1.36
    idenote
    -1.32
    ________
    -1.31
    Department
    -1.30
    POSITIVE LOGITS
    ł
    2.16
    ivat
    1.69
    ¿
    1.63
    »¿
    1.59
    IJ
    1.58
    ¡
    1.56
    entes
    1.56
    ivated
    1.55
    Ľ
    1.54
    ¤
    1.54
    Activations Density 0.018%

    No Known Activations