© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27080
    Prev
    Next
    INDEX
    Explanations

    references to a particular place or establishment named "Bar."

    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
    369
    +0.22
    1.3%
    209
    +0.12
    0.7%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    443
    +0.22
    0.03
    369
    +0.12
    0.03
    194
    +0.11
    0.03
    Negative Logits
    ĵ
    -1.85
    usterity
    -1.84
    ij
    -1.78
     entirety
    -1.60
     her
    -1.59
    Ń
    -1.51
     hers
    -1.51
    forth
    -1.47
    tik
    -1.46
    ¯
    -1.45
    POSITIVE LOGITS
    wick
    2.10
    oque
    1.98
    rington
    1.94
    ringer
    1.84
    riers
    1.74
    becue
    1.70
    ajas
    1.67
    rett
    1.59
    zol
    1.59
    ilage
    1.59
    Activations Density 8.074%

    No Known Activations