© 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. 28596
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "was"

    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
    340
    +0.16
    0.9%
    119
    +0.13
    0.7%
    112
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    32
    +0.16
    0.14
    146
    +0.13
    0.12
    335
    +0.12
    0.11
    Negative Logits
    ¡
    -2.26
    ://
    -1.72
    £
    -1.62
    Ĵ
    -1.58
    ģ
    -1.54
    thouse
    -1.49
     “
    -1.48
    aeda
    -1.43
    ĭ
    -1.42
    ³
    -1.41
    POSITIVE LOGITS
    ome
    1.69
    uality
    1.53
    ails
    1.45
    hell
    1.41
    kers
    1.40
    ?'
    1.37
    ]]
    1.35
    keys
    1.35
    rbrace
    1.35
    ore
    1.34
    Activations Density 0.300%

    No Known Activations