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

    Neuronpedia

    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. 2-MLP-SM
    11. 25473
    Prev
    Next
    INDEX
    Explanations

    the presence of tokens related to "yt" that signify different states or forms of content

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    23
    +0.18
    1.0%
    156
    +0.16
    0.9%
    39
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.18
    0.04
    374
    +0.16
    0.02
    329
    +0.14
    0.02
    Negative Logits
    ½
    -1.86
    Ń
    -1.77
    ¬
    -1.74
    blockList
    -1.70
    cción
    -1.67
    acea
    -1.64
    krit
    -1.59
    ī
    -1.50
    temporal
    -1.45
    [/
    -1.44
    POSITIVE LOGITS
    ioned
    1.66
     briefly
    1.59
     raise
    1.58
     please
    1.55
     yours
    1.53
     few
    1.53
    uddle
    1.53
     there
    1.50
    quee
    1.49
     suffice
    1.48
    Activations Density 0.522%

    No Known Activations