© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 30347
    Prev
    Next
    INDEX
    Explanations

    references to meals and their preparation

    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
    164
    +0.15
    0.8%
    61
    +0.13
    0.7%
    430
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    389
    +0.15
    0.03
    356
    +0.13
    0.03
    377
    +0.12
    0.03
    Negative Logits
     peaks
    -1.55
     streams
    -1.49
    quit
    -1.46
     weeds
    -1.45
    rains
    -1.45
    about
    -1.42
    onders
    -1.41
    wikipedia
    -1.41
    blogspot
    -1.40
     rivers
    -1.39
    POSITIVE LOGITS
    »¿
    1.79
    ylase
    1.64
    ux
    1.61
    yla
    1.51
    ately
    1.46
     number
    1.39
    oplastic
    1.39
    ctomy
    1.39
     alla
    1.38
     (;
    1.34
    Activations Density 0.016%

    No Known Activations