© 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. 2-MLP-SM
    11. 24501
    Prev
    Next
    INDEX
    Explanations

    references to experimental methods and data

    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
    135
    +0.15
    0.9%
    23
    +0.13
    0.7%
    50
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    135
    +0.15
    0.02
    196
    +0.13
    0.02
    50
    +0.12
    0.01
    Negative Logits
    ligt
    -1.73
    ál
    -1.57
    uan
    -1.55
     omissions
    -1.43
    bels
    -1.41
     error
    -1.39
     guideline
    -1.39
    PLIED
    -1.37
     difference
    -1.37
    stro
    -1.34
    POSITIVE LOGITS
    ĻĤ
    3.60
    ¿½
    3.15
    Ĺ
    3.12
    ĵ
    2.91
    Ģ
    2.86
    Ķ
    2.83
    ĩ
    2.75
    ĭ
    2.75
    ĸ
    2.73
    ª
    2.69
    Activations Density 0.112%

    No Known Activations