© 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 EvalsExportsAPI 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. 28371
    Prev
    Next
    INDEX
    Explanations

    references to a specific software framework or library, particularly Django

    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
    373
    +0.13
    0.7%
    237
    +0.13
    0.7%
    63
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    317
    +0.13
    0.01
    373
    +0.13
    0.01
    465
    +0.11
    0.01
    Negative Logits
    'll
    -1.72
    ?'
    -1.68
    '?"
    -1.51
    ll
    -1.50
    ,''
    -1.48
    .''
    -1.43
    toString
    -1.40
    big
    -1.35
    ras
    -1.35
     worth
    -1.35
    POSITIVE LOGITS
    erate
    1.64
    ruptcy
    1.48
    amine
    1.46
    ¡
    1.42
    acular
    1.41
    blower
    1.41
     HN
    1.41
    ugu
    1.41
     arsenal
    1.39
    cif
    1.37
    Activations Density 0.009%

    No Known Activations