© 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. 2-MLP-SM
    11. 25761
    Prev
    Next
    INDEX
    Explanations

    the repeated use of the phrase "of" 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/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
    409
    +0.11
    0.6%
    238
    +0.11
    0.6%
    468
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    461
    +0.11
    0.06
    468
    +0.11
    0.05
    409
    +0.10
    0.06
    Negative Logits
     Doll
    -1.68
     preponderance
    -1.45
     vast
    -1.44
     yourself
    -1.41
     hypothesis
    -1.39
     dogs
    -1.39
     adults
    -1.38
     neonates
    -1.36
     canine
    -1.34
     dog
    -1.33
    POSITIVE LOGITS
    ĥ½
    2.70
    Ī
    2.27
    ĻĤ
    2.24
    ´
    2.09
    »¿
    2.06
    Ń
    2.01
    ĺ
    1.98
    ŀ
    1.96
    ©
    1.91
    ª
    1.89
    Activations Density 0.191%

    No Known Activations