© 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. 30414
    Prev
    Next
    INDEX
    Explanations

    database query commands

    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
    +0.15
    0.9%
    144
    +0.10
    0.6%
    181
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    345
    +0.15
    0.01
    181
    +0.10
    0.01
    301
    +0.10
    0.01
    Negative Logits
    ĥ½
    -2.23
    ½
    -2.21
    ¿
    -2.06
    ľĵ
    -1.82
    ĥ
    -1.82
    »
    -1.81
    isance
    -1.80
    ¬
    -1.80
    ĭ
    -1.78
    ·¸
    -1.78
    POSITIVE LOGITS
    naire
    2.11
    notes
    1.78
     aid
    1.74
    ég
    1.71
     arsenal
    1.70
     aids
    1.68
    gun
    1.68
    able
    1.63
    bank
    1.63
     drafts
    1.60
    Activations Density 0.014%

    No Known Activations