© 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. 0-MLP-SM
    11. 28105
    Prev
    Next
    INDEX
    Explanations

    references to events, dates, or situations related to community or collective experiences

    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
    185
    +0.20
    1.1%
    47
    +0.14
    0.8%
    460
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.20
    0.55
    56
    +0.14
    0.17
    203
    +0.11
    0.37
    Negative Logits
     stride
    -1.50
    fellow
    -1.47
     incub
    -1.45
     pace
    -1.43
     trained
    -1.37
    OTA
    -1.37
     Scout
    -1.37
     undercover
    -1.35
     tailor
    -1.32
    quit
    -1.31
    POSITIVE LOGITS
    ĵ
    2.18
    ¢
    1.82
    ľĵ
    1.80
    »¿
    1.75
    ¿½
    1.70
    ¦
    1.68
    ational
    1.66
    inals
    1.65
    Ĵ
    1.63
    ģ
    1.63
    Activations Density 3.896%

    No Known Activations