© 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. 29416
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude

    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
    73
    +0.13
    0.7%
    277
    +0.11
    0.6%
    376
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    277
    +0.13
    0.02
    103
    +0.11
    0.02
    347
    +0.10
    0.01
    Negative Logits
    anson
    -1.66
    chte
    -1.59
    epithelial
    -1.54
    atosis
    -1.53
    EP
    -1.52
    yler
    -1.50
    ankton
    -1.50
    chel
    -1.45
    illin
    -1.44
    Hg
    -1.43
    POSITIVE LOGITS
     ones
    1.95
    ities
    1.85
    nier
    1.65
    ités
    1.60
    ity
    1.60
     conditions
    1.58
    pieces
    1.53
    gements
    1.52
     schemes
    1.51
     situation
    1.51
    Activations Density 0.025%

    No Known Activations