© 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. 30575
    Prev
    Next
    INDEX
    Explanations

    HTML anchor tags with specific attributes

    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
    61
    +0.12
    0.7%
    261
    +0.12
    0.7%
    144
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    61
    +0.12
    0.01
    261
    +0.12
    0.01
    404
    +0.12
    0.01
    Negative Logits
    µ
    -2.59
    ¢
    -2.16
    ¿
    -2.15
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -2.02
    Ł
    -1.98
    ↵↵
    -1.98
    -1.98
    -1.98
    -1.98
    <|outofrange|>
    -1.98
    POSITIVE LOGITS
    icul
    1.88
    ball
    1.61
     passions
    1.58
    ahu
    1.57
    subsec
    1.54
    fered
    1.53
    {}{
    1.52
    nell
    1.50
    icip
    1.49
    evidence
    1.42
    Activations Density 0.011%

    No Known Activations