© 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. 26739
    Prev
    Next
    INDEX
    Explanations

    the term "oval" in various contexts

    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
    376
    +0.12
    0.7%
    260
    +0.12
    0.7%
    392
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.12
    0.01
    260
    +0.12
    0.01
    243
    +0.11
    0.01
    Negative Logits
    »¿
    -2.39
    Ĥ¬
    -1.97
    ĥ½
    -1.91
    ĵ
    -1.65
    unnumbered
    -1.60
    ľ
    -1.60
    ¿
    -1.57
    rian
    -1.54
    lying
    -1.53
    ´
    -1.50
    POSITIVE LOGITS
    ista
    1.60
    naire
    1.59
    enium
    1.53
    erna
    1.49
    istor
    1.47
    etica
    1.45
    FW
    1.42
    PCR
    1.41
    endor
    1.41
    eni
    1.41
    Activations Density 0.007%

    No Known Activations