© 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. 28048
    Prev
    Next
    INDEX
    Explanations

    chemical compounds, particularly those containing ethyl groups

    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
    71
    +0.13
    0.7%
    13
    +0.12
    0.7%
    111
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    13
    +0.13
    0.01
    57
    +0.12
    0.01
    9
    +0.11
    0.01
    Negative Logits
    forth
    -1.57
     '</
    -1.54
    rely
    -1.51
    xa
    -1.45
    unn
    -1.43
     close
    -1.42
     forth
    -1.41
    unnumbered
    -1.41
    rices
    -1.37
    az
    -1.36
    POSITIVE LOGITS
    ĻĤ
    4.18
    £
    3.65
    ļ
    3.58
    §
    3.55
    ¥
    3.48
    º
    3.46
    ¨
    3.42
    ¬
    3.39
    ģ
    3.37
    Ń
    3.34
    Activations Density 0.021%

    No Known Activations