© 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. 27108
    Prev
    Next
    INDEX
    Explanations

    references to shaped or patterned objects

    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
    376
    +0.16
    0.9%
    156
    +0.15
    0.9%
    351
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    167
    +0.16
    0.01
    268
    +0.15
    0.01
    351
    +0.13
    0.01
    Negative Logits
     coast
    -1.62
    sson
    -1.48
    lla
    -1.46
    ainted
    -1.41
    aliana
    -1.39
    ITED
    -1.34
    ited
    -1.33
     attracted
    -1.30
     Abor
    -1.29
    erald
    -1.28
    POSITIVE LOGITS
    staff
    1.68
    phal
    1.48
    dimen
    1.47
    paces
    1.47
    ahead
    1.44
    agram
    1.43
     (<
    1.39
    estine
    1.37
     fields
    1.36
    PRINT
    1.35
    Activations Density 0.029%

    No Known Activations