© 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 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. 28625
    Prev
    Next
    INDEX
    Explanations

    references to the React framework

    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
    67
    +0.13
    0.7%
    72
    +0.12
    0.7%
    256
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.13
    0.02
    353
    +0.12
    0.02
    256
    +0.11
    0.01
    Negative Logits
    ¿½
    -2.18
    ¿
    -2.11
    »¿
    -1.77
    ¬
    -1.75
    ĨĴ
    -1.70
    ´
    -1.66
    ²
    -1.64
    «
    -1.57
    ))$.
    -1.56
     ')
    -1.55
    POSITIVE LOGITS
    nik
    1.66
    bars
    1.66
    eless
    1.57
    nal
    1.56
    ivated
    1.56
    ÅĨ
    1.54
    ivat
    1.52
    essed
    1.52
    papers
    1.51
    ificial
    1.48
    Activations Density 1.670%

    No Known Activations