© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-MLP-SM
    11. 25603
    Prev
    Next
    INDEX
    Explanations

    interactions and requests for help

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    320
    +0.11
    0.6%
    149
    +0.11
    0.6%
    179
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    470
    +0.11
    0.05
    500
    +0.11
    0.02
    397
    +0.10
    0.05
    Negative Logits
     tons
    -1.63
    ¥
    -1.59
    ²
    -1.50
     NOTICE
    -1.50
     NEWS
    -1.49
     SYSTEM
    -1.47
    info
    -1.44
    º
    -1.41
     sleeve
    -1.39
     LOT
    -1.38
    POSITIVE LOGITS
     vacated
    1.61
    ]{}.
    1.54
     characterized
    1.48
     combat
    1.46
    vez
    1.41
    vre
    1.40
    iates
    1.38
     alone
    1.37
    ôle
    1.35
     himself
    1.34
    Activations Density 0.662%

    No Known Activations