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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27770
    Prev
    Next
    INDEX
    Explanations

    instances of the word "obi."

    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
    181
    +0.12
    0.7%
    172
    +0.12
    0.7%
    450
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    181
    +0.12
    0.01
    172
    +0.12
    0.01
    450
    +0.11
    0.01
    Negative Logits
    Ļª
    -1.91
    ©
    -1.88
    hip
    -1.57
     converse
    -1.50
    lando
    -1.48
    ĨĴ
    -1.46
     č
    -1.44
    ")]
    -1.43
     latter
    -1.43
     ?"
    -1.41
    POSITIVE LOGITS
    assic
    1.82
    fileID
    1.73
    omorphic
    1.63
    uscript
    1.57
    plots
    1.56
    scripts
    1.52
    istically
    1.50
    antry
    1.49
    elong
    1.48
    shots
    1.48
    Activations Density 0.005%

    No Known Activations