© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 26963
    Prev
    Next
    INDEX
    Explanations

    references to legal cases or court citations

    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
    47
    +0.13
    0.7%
    146
    +0.11
    0.6%
    449
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    171
    +0.13
    -0.02
    146
    +0.11
    0.04
    493
    +0.11
    0.05
    Negative Logits
    edly
    -1.62
     gin
    -1.59
    acht
    -1.56
    meal
    -1.53
    iousness
    -1.49
    enance
    -1.40
     quietly
    -1.39
     beers
    -1.36
    thren
    -1.35
     humour
    -1.34
    POSITIVE LOGITS
     etc
    1.46
    TRODUCTION
    1.41
    cias
    1.40
    =".
    1.38
     ""
    1.35
     \-
    1.33
    ticas
    1.31
    umab
    1.31
     \[[@
    1.31
    \[[@
    1.28
    Activations Density 1.637%

    No Known Activations