© 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 EvalsExportsAPI 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. 29163
    Prev
    Next
    INDEX
    Explanations

    instances of the word "fat."

    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
    410
    +0.17
    1.0%
    274
    +0.14
    0.8%
    467
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.17
    0.01
    274
    +0.14
    0.01
    111
    +0.12
    0.01
    Negative Logits
     distance
    -1.50
     sour
    -1.34
     perm
    -1.34
     osm
    -1.30
     replacing
    -1.30
     saline
    -1.29
    rs
    -1.29
    ams
    -1.29
    URAL
    -1.26
    CHO
    -1.22
    POSITIVE LOGITS
    furt
    2.15
    enstein
    1.65
    mouth
    1.56
    hold
    1.51
    chester
    1.51
    pshire
    1.49
    rier
    1.49
    fire
    1.48
    haven
    1.47
    hammer
    1.46
    Activations Density 0.030%

    No Known Activations