© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-MLP-SM
    11. 25703
    Prev
    Next
    INDEX
    Explanations

    statements about the subject or features of something

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    510
    +0.13
    0.7%
    419
    +0.12
    0.7%
    369
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    272
    +0.13
    0.05
    510
    +0.12
    0.04
    419
    +0.12
    0.03
    Negative Logits
    ¿½
    -1.81
     |
    -1.74
     \|
    -1.68
     \{\
    -1.66
    terday
    -1.52
    č↵
    -1.47
     |\
    -1.46
    ª
    -1.43
     wis
    -1.43
    ŀ
    -1.40
    POSITIVE LOGITS
    legate
    1.55
    aña
    1.53
     attention
    1.49
     capacity
    1.42
    place
    1.41
    ÃŃa
    1.40
    fessor
    1.40
     courage
    1.40
    claim
    1.38
    posium
    1.38
    Activations Density 0.384%

    No Known Activations