© 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. 26378
    Prev
    Next
    INDEX
    Explanations

    instances of the word "selection" 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
    376
    +0.14
    0.8%
    408
    +0.13
    0.7%
    156
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    420
    +0.14
    0.02
    408
    +0.13
    0.02
    358
    +0.12
    0.02
    Negative Logits
    ĥ½
    -2.16
    Į
    -2.00
    §
    -1.98
    ĨĴ
    -1.92
    ĸ´
    -1.80
     anything
    -1.68
    edes
    -1.64
    ĻĤ
    -1.61
    ľ
    -1.57
    orems
    -1.56
    POSITIVE LOGITS
    ately
    1.77
    fluid
    1.57
     controls
    1.55
     sources
    1.54
     HPLC
    1.52
     valve
    1.47
     variables
    1.44
     area
    1.42
     dates
    1.41
     issue
    1.41
    Activations Density 0.036%

    No Known Activations