© 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. 30131
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual named Jim

    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
    156
    +0.16
    0.9%
    376
    +0.15
    0.9%
    410
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    357
    +0.16
    0.03
    74
    +0.15
    0.02
    59
    +0.14
    0.02
    Negative Logits
    ¿½
    -2.05
    Ļª
    -2.00
     superior
    -1.79
     child
    -1.75
    "?"
    -1.71
     latter
    -1.65
     previous
    -1.57
    ĥ
    -1.55
    ort
    -1.53
     former
    -1.53
    POSITIVE LOGITS
    aho
    1.95
    mie
    1.90
    pson
    1.77
    pton
    1.75
    inx
    1.65
     DOI
    1.64
    icillin
    1.60
    omycin
    1.58
    oj
    1.56
    ilee
    1.55
    Activations Density 0.010%

    No Known Activations