© 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. 29495
    Prev
    Next
    INDEX
    Explanations

    strong adjectives indicating high quality or excellence

    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
    78
    +0.14
    0.8%
    29
    +0.13
    0.7%
    111
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.14
    0.04
    170
    +0.13
    0.04
    311
    +0.13
    0.04
    Negative Logits
    andy
    -1.78
    enson
    -1.65
    ource
    -1.59
    oin
    -1.57
    arden
    -1.54
    onz
    -1.52
    zione
    -1.50
    ault
    -1.49
    xtures
    -1.49
    ging
    -1.47
    POSITIVE LOGITS
     enough
    2.02
     contrasted
    1.53
     speaking
    1.42
     %.
    1.41
     bun
    1.41
     (>
    1.32
     Lear
    1.32
    rics
    1.30
     respectable
    1.30
     mob
    1.28
    Activations Density 0.118%

    No Known Activations