© 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. 28021
    Prev
    Next
    INDEX
    Explanations

    the word "it" used repeatedly in various contexts

    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
    473
    +0.14
    0.8%
    423
    +0.13
    0.7%
    154
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.14
    0.22
    185
    +0.13
    0.18
    165
    +0.12
    0.17
    Negative Logits
    ¨
    -2.70
    ®
    -2.60
    ¿½
    -2.34
    §
    -2.25
    Ĺ
    -2.18
    »¿
    -2.18
    Ļ
    -2.15
    ¤
    -2.10
    °
    -2.03
    Ł
    -2.01
    POSITIVE LOGITS
    iator
    1.56
    uras
    1.54
     _
    1.50
     **_
    1.40
    ."_
    1.39
    **
    1.37
    uated
    1.37
     Kamp
    1.36
    bor
    1.35
     each
    1.35
    Activations Density 0.401%

    No Known Activations