© 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. 30757
    Prev
    Next
    INDEX
    Explanations

    references to rental agreements and rental services

    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
    +0.18
    1.0%
    376
    +0.13
    0.8%
    445
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    449
    +0.18
    0.02
    255
    +0.13
    0.02
    445
    +0.13
    0.02
    Negative Logits
    ching
    -1.69
    ÑĤÑĮ
    -1.57
    fare
    -1.56
    ÑİÑĤ
    -1.53
    rocyte
    -1.50
    ÑĢоÑģ
    -1.43
    hem
    -1.43
    Ñħ
    -1.41
     CDC
    -1.40
    iling
    -1.39
    POSITIVE LOGITS
    ·¸
    1.70
     possessions
    1.70
    ĻĤ
    1.65
    taire
    1.46
     occasions
    1.41
    esian
    1.41
    worth
    1.40
     items
    1.39
     assets
    1.38
     instruments
    1.38
    Activations Density 0.013%

    No Known Activations