© 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. 26976
    Prev
    Next
    INDEX
    Explanations

    actions or commands directed towards an audience or entity

    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
    3
    +0.14
    0.8%
    193
    +0.13
    0.7%
    226
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.14
    0.38
    151
    +0.13
    0.31
    434
    +0.11
    0.30
    Negative Logits
    º
    -4.14
    Ķ
    -3.84
    ¶
    -3.79
    Ĥ¬
    -3.72
    ´
    -3.71
    Į
    -3.62
    ł
    -3.61
    ¥
    -3.59
    ¯
    -3.58
    §
    -3.54
    POSITIVE LOGITS
    ering
    1.62
    ados
    1.62
    erals
    1.62
    ressor
    1.56
    apters
    1.55
     expect
    1.46
    idenote
    1.44
     import
    1.43
    resses
    1.43
    veis
    1.41
    Activations Density 1.660%

    No Known Activations