© 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. 26732
    Prev
    Next
    INDEX
    Explanations

    phrases indicating mandatory requirements or obligations

    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
    +0.20
    1.1%
    501
    +0.12
    0.6%
    310
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    501
    +0.20
    0.04
    310
    +0.12
    0.04
    101
    +0.11
    0.03
    Negative Logits
    erated
    -1.64
    roup
    -1.48
    reet
    -1.48
    liver
    -1.46
    CNN
    -1.43
    opoulos
    -1.42
    ---|---|---
    -1.41
    POINT
    -1.40
    founded
    -1.40
     possible
    -1.39
    POSITIVE LOGITS
    orate
    1.74
     gaps
    1.56
     ingredient
    1.53
     refrig
    1.44
     blank
    1.44
     missing
    1.42
     print
    1.41
     vest
    1.38
    encing
    1.36
     dressing
    1.34
    Activations Density 2.326%

    No Known Activations