© 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. 26767
    Prev
    Next
    INDEX
    Explanations

    references to software versions and their associated characteristics

    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
    142
    +0.12
    0.7%
    185
    +0.12
    0.7%
    170
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    128
    +0.12
    0.01
    189
    +0.12
    0.03
    142
    +0.12
    0.03
    Negative Logits
    ¹
    -2.00
    ¯
    -1.91
    ĩ
    -1.89
    ĻĤ
    -1.87
    ī
    -1.78
    Ģ
    -1.78
    ı
    -1.69
    »¿
    -1.67
    ”,
    -1.67
    Īĺ
    -1.63
    POSITIVE LOGITS
    istine
    1.48
     mat
    1.46
     seasons
    1.45
    sembled
    1.41
    itely
    1.40
    edly
    1.39
    iet
    1.36
    queous
    1.33
     Condition
    1.33
     tub
    1.31
    Activations Density 0.134%

    No Known Activations