© 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. 25697
    Prev
    Next
    INDEX
    Explanations

    references to programming or technical terms, particularly in relation to system functionality or documentation

    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
    176
    +0.13
    0.7%
    424
    +0.13
    0.7%
    267
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    125
    +0.13
    0.12
    370
    +0.13
    0.11
    194
    +0.11
    0.10
    Negative Logits
     review
    -1.57
    ĻĤ
    -1.56
     debate
    -1.45
    utor
    -1.45
    igan
    -1.44
    orts
    -1.44
    anc
    -1.42
    posium
    -1.37
    ivers
    -1.34
    rer
    -1.34
    POSITIVE LOGITS
     same
    1.75
     tend
    1.40
     hers
    1.39
     cliffs
    1.36
    acity
    1.36
     sunk
    1.36
     chosen
    1.33
    lium
    1.31
     distances
    1.31
     worn
    1.31
    Activations Density 2.955%

    No Known Activations