© 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. 30475
    Prev
    Next
    INDEX
    Explanations

    LaTeX formatting commands

    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
    364
    +0.11
    0.6%
    225
    +0.11
    0.6%
    381
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    381
    +0.11
    0.01
    3
    +0.11
    0.01
    137
    +0.10
    0.01
    Negative Logits
     inception
    -1.59
     away
    -1.57
     none
    -1.54
     edge
    -1.54
     hers
    -1.53
     solid
    -1.52
     boiling
    -1.51
     down
    -1.51
     numerically
    -1.50
    "?"
    -1.49
    POSITIVE LOGITS
    ĻĤ
    1.90
    ceedings
    1.79
    aña
    1.69
    reader
    1.67
    £
    1.66
    estead
    1.65
    thouse
    1.63
    template
    1.61
    eca
    1.60
    story
    1.58
    Activations Density 0.017%

    No Known Activations