© 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. 25471
    Prev
    Next
    INDEX
    Explanations

    terms related to database management and security

    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
    414
    +0.13
    0.7%
    23
    +0.13
    0.7%
    116
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.13
    0.06
    345
    +0.13
    0.09
    232
    +0.11
    0.09
    Negative Logits
    arma
    -1.57
    attle
    -1.55
    #:
    -1.52
    Cause
    -1.51
    town
    -1.50
    cheat
    -1.42
    áĢ¬
    -1.42
    ressor
    -1.40
    llo
    -1.39
    óg
    -1.39
    POSITIVE LOGITS
     accordingly
    1.94
    stood
    1.78
    ¿½
    1.68
    ¯
    1.57
    ĸ´
    1.56
    onical
    1.52
    Ĭ
    1.48
     continued
    1.47
     ourselves
    1.45
     thereafter
    1.44
    Activations Density 1.880%

    No Known Activations