© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 28710
    Prev
    Next
    INDEX
    Explanations

    the term "ret" and its variations 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
    388
    +0.14
    0.8%
    485
    +0.11
    0.7%
    328
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    388
    +0.14
    0.03
    328
    +0.11
    0.02
    49
    +0.11
    0.02
    Negative Logits
    ]>
    -1.63
    obbsee
    -1.63
    >$
    -1.56
    xture
    -1.54
    annel
    -1.45
    urane
    -1.44
    STM
    -1.43
     grown
    -1.43
    hler
    -1.41
    HI
    -1.38
    POSITIVE LOGITS
    ħ
    2.36
    ģ
    2.27
    ¡
    2.21
    ĻĤ
    2.04
    £
    2.02
    Ģ
    1.95
    IJ
    1.94
     affiliations
    1.91
    į
    1.89
    ¢
    1.81
    Activations Density 0.007%

    No Known Activations