© 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. 29742
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Options" related to configuration or settings

    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
    +0.16
    1.0%
    250
    +0.12
    0.7%
    365
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.16
    0.02
    287
    +0.12
    0.02
    250
    +0.11
    0.02
    Negative Logits
    ĥ½
    -1.74
     her
    -1.66
     href
    -1.66
    cknowled
    -1.65
    ľĵ
    -1.64
    ij
    -1.62
     certain
    -1.59
    ľ
    -1.57
    ¿½
    -1.56
     their
    -1.56
    POSITIVE LOGITS
    ista
    1.94
    boro
    1.83
    cript
    1.68
    ató
    1.67
    kick
    1.66
    bellum
    1.66
    ale
    1.62
    naire
    1.61
     era
    1.60
     arsenal
    1.58
    Activations Density 0.014%

    No Known Activations