© 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. 28175
    Prev
    Next
    INDEX
    Explanations

    references to cooking techniques or ingredients

    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
    307
    +0.12
    0.7%
    274
    +0.12
    0.7%
    81
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.12
    0.03
    105
    +0.12
    0.03
    240
    +0.11
    0.03
    Negative Logits
    áĢ¯
    -1.66
    rish
    -1.66
    Ĺ
    -1.44
    atics
    -1.42
     ')
    -1.42
    awning
    -1.41
    inand
    -1.38
    rella
    -1.35
    ´
    -1.34
    olor
    -1.33
    POSITIVE LOGITS
    enstein
    1.72
    esto
    1.65
    igent
    1.59
    ensing
    1.43
    potent
    1.41
    eria
    1.41
    ibrary
    1.40
     Rptr
    1.39
    ergy
    1.38
    oku
    1.38
    Activations Density 0.029%

    No Known Activations