© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 26848
    Prev
    Next
    INDEX
    Explanations

    repeated mentions or references to "messages."

    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
    329
    +0.13
    0.7%
    338
    +0.12
    0.7%
    325
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    226
    +0.13
    0.14
    257
    +0.12
    0.13
    147
    +0.12
    0.13
    Negative Logits
    ¿
    -2.29
    İ
    -2.26
    ¦
    -2.25
    ·
    -2.06
    ¿½
    -2.02
    ĥ½
    -2.00
    ı
    -2.00
    »¿
    -1.95
    Ľ
    -1.94
    ĸ´
    -1.84
    POSITIVE LOGITS
    opters
    1.58
    >]
    1.52
    apers
    1.51
     them
    1.42
     occasional
    1.41
    opter
    1.41
    TP
    1.38
    heter
    1.38
    oste
    1.37
     unlimited
    1.36
    Activations Density 0.231%

    No Known Activations