© 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. 29997
    Prev
    Next
    INDEX
    Explanations

    phrases that include the definite article "the" and instances of "in" used in context

    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
    56
    +0.13
    0.7%
    18
    +0.12
    0.7%
    116
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.13
    0.42
    98
    +0.12
    0.24
    228
    +0.12
    0.34
    Negative Logits
    imus
    -1.82
    icum
    -1.72
    uing
    -1.63
    amping
    -1.61
    orea
    -1.61
    swift
    -1.58
    #:
    -1.57
    wort
    -1.50
     /*!<
    -1.49
    ↵³³
    -1.48
    POSITIVE LOGITS
    ¥
    1.92
    ¿½
    1.75
     payroll
    1.74
    ·
    1.68
     obsc
    1.59
     age
    1.58
    ł
    1.51
     sight
    1.51
     decades
    1.46
    ģ
    1.45
    Activations Density 5.105%

    No Known Activations