© 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 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. 29388
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Load" 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%
    19
    +0.13
    0.8%
    29
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    452
    +0.14
    0.01
    19
    +0.13
    0.01
    146
    +0.11
    0.01
    Negative Logits
    't
    -2.01
    usement
    -1.93
    aling
    -1.69
    oved
    -1.55
     afraid
    -1.54
    onym
    -1.52
    athan
    -1.51
     faint
    -1.50
     ')
    -1.49
    uses
    -1.49
    POSITIVE LOGITS
    ings
    2.27
    ership
    1.81
    ers
    1.78
    erne
    1.71
    starter
    1.70
    ¢
    1.67
    able
    1.65
    ÃŃs
    1.64
    ingly
    1.64
    ies
    1.62
    Activations Density 3.561%

    No Known Activations