© 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 EvalsExportsAPI 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. 28522
    Prev
    Next
    INDEX
    Explanations

    questions starting with "how."

    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
    475
    +0.15
    0.9%
    379
    +0.12
    0.7%
    260
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    459
    +0.15
    0.08
    179
    +0.12
    0.08
    496
    +0.11
    0.08
    Negative Logits
    une
    -1.60
    onies
    -1.60
    tis
    -1.46
    .",
    -1.45
    ogly
    -1.38
    ilent
    -1.37
    ureus
    -1.36
    orus
    -1.36
     Invention
    -1.35
    EP
    -1.32
    POSITIVE LOGITS
     resort
    1.47
    hou
    1.45
    ]>
    1.43
     bomber
    1.43
    áĢ¬
    1.42
     basketball
    1.38
    imir
    1.33
     speeds
    1.32
    iator
    1.32
     model
    1.31
    Activations Density 0.064%

    No Known Activations