© 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. 28049
    Prev
    Next
    INDEX
    Explanations

    references to activated or enabled systems and features

    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
    376
    +0.18
    1.0%
    443
    +0.14
    0.8%
    156
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    443
    +0.18
    0.01
    260
    +0.14
    0.01
    217
    +0.12
    0.01
    Negative Logits
    ritic
    -1.64
    romycin
    -1.58
    okin
    -1.50
    erson
    -1.49
    essen
    -1.45
    rox
    -1.41
    reet
    -1.36
    ket
    -1.36
    inated
    -1.35
    heastern
    -1.35
    POSITIVE LOGITS
     anonymity
    1.51
    erably
    1.49
    =”
    1.48
    ence
    1.38
    ĻĤ
    1.37
     disabled
    1.34
    heets
    1.33
     unnamed
    1.31
     gaps
    1.29
     accuracy
    1.27
    Activations Density 0.030%

    No Known Activations