© 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. 29308
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest conditions or stipulations regarding a subject

    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
    222
    +0.12
    0.7%
    432
    +0.12
    0.7%
    154
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.12
    0.08
    438
    +0.12
    0.07
    56
    +0.11
    0.01
    Negative Logits
    angular
    -1.53
    wise
    -1.48
    maker
    -1.42
     contributed
    -1.40
     signed
    -1.37
     serving
    -1.34
    igned
    -1.31
     transmembrane
    -1.30
     Line
    -1.29
    pires
    -1.29
    POSITIVE LOGITS
    than
    1.71
    ping
    1.70
    rah
    1.69
     than
    1.68
    aline
    1.65
    setlength
    1.60
    romy
    1.59
    phy
    1.50
    hus
    1.48
    )|$(
    1.48
    Activations Density 4.697%

    No Known Activations