© 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. 0-MLP-SM
    11. 28154
    Prev
    Next
    INDEX
    Explanations

    words related to XML and data handling

    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
    400
    +0.13
    0.7%
    371
    +0.13
    0.7%
    424
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.13
    0.43
    209
    +0.13
    0.28
    402
    +0.12
    0.25
    Negative Logits
    izumab
    -1.80
    aiser
    -1.57
    wn
    -1.56
    dess
    -1.55
    renn
    -1.55
     forth
    -1.53
    raine
    -1.49
    www
    -1.49
    riv
    -1.48
    úblic
    -1.46
    POSITIVE LOGITS
    ¨
    2.68
    ł
    2.37
    ¼
    2.31
    ¬
    2.22
    ½
    2.20
    ģ
    2.18
    Īĺ
    2.16
    Ļª
    2.16
    ij
    2.08
    °
    2.07
    Activations Density 1.566%

    No Known Activations