© 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. 29250
    Prev
    Next
    INDEX
    Explanations

    terms related to the compression and arrangement of materials or substances

    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
    +0.20
    1.1%
    444
    +0.17
    1.0%
    164
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    444
    +0.20
    0.01
    46
    +0.17
    0.01
    40
    +0.12
    0.01
    Negative Logits
     slightest
    -1.53
    aliana
    -1.50
     celebrated
    -1.50
     Pref
    -1.45
     dawn
    -1.44
    uka
    -1.44
    ours
    -1.42
    elijk
    -1.39
     preference
    -1.39
    oured
    -1.38
    POSITIVE LOGITS
    ĻĤ
    1.92
    tees
    1.84
    arts
    1.78
     sensing
    1.70
    iencies
    1.61
    ifle
    1.56
    estry
    1.52
    erve
    1.50
    tee
    1.49
    amycin
    1.49
    Activations Density 0.008%

    No Known Activations