© 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. 29921
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Introduction."

    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
    389
    +0.12
    0.7%
    380
    +0.12
    0.7%
    250
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    389
    +0.12
    0.01
    454
    +0.12
    0.01
    380
    +0.11
    0.01
    Negative Logits
    isher
    -1.74
     luck
    -1.67
    derer
    -1.60
    isance
    -1.53
     answer
    -1.46
    arte
    -1.45
    eanor
    -1.44
    pling
    -1.42
    asta
    -1.42
    iousness
    -1.41
    POSITIVE LOGITS
    lane
    1.57
     lanes
    1.41
    pend
    1.40
    istani
    1.37
    clusive
    1.37
    cript
    1.36
    UP
    1.34
    EMENT
    1.33
    Script
    1.33
    mathrsfs
    1.32
    Activations Density 0.017%

    No Known Activations