© 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. 25743
    Prev
    Next
    INDEX
    Explanations

    references to digital devices

    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
    156
    +0.29
    1.8%
    365
    +0.15
    0.9%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.29
    0.02
    223
    +0.15
    0.02
    205
    +0.12
    0.02
    Negative Logits
     ↵
    -1.96
    <|outofrange|>
    -1.96
    -1.96
    ↵↵
    -1.96
    ↵
    -1.96
    -1.96
     ↵
    -1.96
    ↵
    -1.96
    -1.96
    -1.96
    POSITIVE LOGITS
    caster
    1.96
    illar
    1.74
    iac
    1.72
    aho
    1.72
    eto
    1.68
    urgical
    1.65
    etting
    1.64
    OTE
    1.60
    fors
    1.59
    cript
    1.56
    Activations Density 0.020%

    No Known Activations