© 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. 0-MLP-SM
    6. 27831
    Prev
    Next
    INDEX
    Explanations

    references to user profiles

    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
    43
    +0.13
    0.8%
    269
    +0.12
    0.7%
    178
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    178
    +0.13
    0.02
    43
    +0.12
    0.01
    269
    +0.12
    0.01
    Negative Logits
    ĥ½
    -4.11
    Ĥ
    -3.83
    ¤
    -3.79
    ķ
    -3.67
    §
    -3.64
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -3.54
    ¿½
    -3.53
    Ĥ¬
    -3.52
    ĺ
    -3.52
    ³
    -3.52
    POSITIVE LOGITS
     (“
    1.81
     area
    1.69
     apparatus
    1.67
    styles
    1.66
    aggio
    1.65
    holder
    1.61
    album
    1.61
    (@"
    1.61
    vier
    1.60
    books
    1.59
    Activations Density 0.013%

    No Known Activations