© 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. 28979
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "get" and its variations in function calls

    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
    +0.15
    0.8%
    193
    +0.15
    0.8%
    351
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    193
    +0.15
    0.06
    270
    +0.15
    0.04
    349
    +0.11
    0.04
    Negative Logits
    unt
    -1.80
    inen
    -1.71
    ask
    -1.66
    ¤
    -1.60
    itting
    -1.58
     ?"
    -1.52
    unc
    -1.51
    "`
    -1.46
    oor
    -1.46
    ?"
    -1.45
    POSITIVE LOGITS
    érie
    1.75
    ĻĤ
    1.69
    abad
    1.63
     aid
    1.59
    eful
    1.57
    ées
    1.57
    ée
    1.56
    arching
    1.53
    minded
    1.51
    chy
    1.45
    Activations Density 3.639%

    No Known Activations