© 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. 29519
    Prev
    Next
    INDEX
    Explanations

    instances of the word "promoted."

    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
    437
    +0.12
    0.6%
    286
    +0.11
    0.6%
    38
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.12
    0.28
    438
    +0.11
    0.25
    338
    +0.11
    0.24
    Negative Logits
    Ŀ
    -4.06
    ¡
    -3.84
    Ĩ
    -3.67
    ĩ
    -3.55
    »¿
    -3.54
    Īĺ
    -3.45
    ģ
    -3.44
    º
    -3.44
    İ
    -3.40
    ·¸
    -3.39
    POSITIVE LOGITS
    irectional
    1.76
    lee
    1.66
     mine
    1.60
    ier
    1.58
    opf
    1.55
    icking
    1.54
    ulic
    1.49
    hole
    1.48
    ume
    1.47
    ering
    1.46
    Activations Density 4.874%

    No Known Activations