© 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. 2-MLP-SM
    11. 25200
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" and its variations in the text

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    500
    +0.13
    0.7%
    255
    +0.12
    0.7%
    155
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    262
    +0.13
    0.04
    500
    +0.12
    0.04
    255
    +0.11
    0.05
    Negative Logits
     operators
    -1.62
     Louisiana
    -1.55
     answers
    -1.53
     UT
    -1.53
    utors
    -1.51
    acles
    -1.46
     Massachusetts
    -1.46
     Operator
    -1.45
     investigators
    -1.44
    smen
    -1.43
    POSITIVE LOGITS
    ¤
    2.06
    Ī
    1.87
    ģ
    1.86
    Ĵ
    1.81
    ĭ
    1.75
    Ń
    1.73
    osph
    1.66
    Ķ
    1.58
    ħ
    1.57
    ½
    1.56
    Activations Density 0.445%

    No Known Activations