© 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. 26147
    Prev
    Next
    INDEX
    Explanations

    references to pricing and costs

    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
    +0.14
    0.9%
    376
    +0.14
    0.8%
    113
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    113
    +0.14
    0.01
    460
    +0.14
    0.01
    249
    +0.13
    0.01
    Negative Logits
     anybody
    -1.71
    orems
    -1.64
    sen
    -1.64
    ndef
    -1.58
    ---|---
    -1.56
    wards
    -1.52
    shore
    -1.47
    tig
    -1.45
     lonely
    -1.45
     anyone
    -1.44
    POSITIVE LOGITS
    illar
    1.76
     situation
    1.73
    ist
    1.72
     issues
    1.69
    haus
    1.64
    °
    1.64
     issue
    1.61
    ģ
    1.60
    lei
    1.59
    orbent
    1.57
    Activations Density 0.084%

    No Known Activations