© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 29736
    Prev
    Next
    INDEX
    Explanations

    patterns of repeated commas in textual data

    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
    121
    +0.14
    0.8%
    159
    +0.12
    0.7%
    483
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.14
    0.36
    23
    +0.12
    0.31
    494
    +0.12
    0.25
    Negative Logits
    poons
    -1.45
    ymbol
    -1.42
    prise
    -1.37
     account
    -1.37
    TypeDef
    -1.35
     occult
    -1.35
     msgid
    -1.34
    Cred
    -1.33
    hip
    -1.32
    еÐ
    -1.31
    POSITIVE LOGITS
    ķ
    2.88
    ²
    2.77
    ¯
    2.73
    ľ
    2.65
    Ķ
    2.57
    ´
    2.52
    ħ
    2.45
    ĸ´
    2.43
    Ļª
    2.41
    ļ
    2.40
    Activations Density 3.082%

    No Known Activations