© 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. 27043
    Prev
    Next
    INDEX
    Explanations

    the word "You" and its variations, indicating a focus on direct address or engagement with the reader

    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
    102
    +0.16
    0.9%
    47
    +0.11
    0.6%
    146
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    124
    +0.16
    0.07
    354
    +0.11
    0.06
    381
    +0.11
    0.05
    Negative Logits
    ·
    -2.08
    ĸ´
    -1.98
    ¾
    -1.92
    ¸
    -1.75
    Ń
    -1.75
    Ĭ
    -1.71
    ¦
    -1.65
    <|outofrange|>
    -1.63
    ↵
    -1.63
    <|outofrange|>
    -1.63
    POSITIVE LOGITS
    +)
    1.93
    $),
    1.68
    $)
    1.58
    anza
    1.58
    antine
    1.53
    )/\
    1.52
    ej
    1.52
    /)
    1.50
    onso
    1.46
    mx
    1.42
    Activations Density 0.118%

    No Known Activations