© 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. 26779
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a location or position

    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
    293
    +0.13
    0.7%
    37
    +0.11
    0.6%
    134
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.13
    0.11
    426
    +0.11
    0.10
    480
    +0.11
    0.10
    Negative Logits
    ĻĤ
    -2.21
    Ľ
    -2.13
    ij
    -2.07
    Ĥ
    -2.06
    ħ
    -2.03
    İ
    -1.93
    £
    -1.85
    ī
    -1.78
    verter
    -1.77
    Ŀ
    -1.76
    POSITIVE LOGITS
    aws
    1.70
     oath
    1.52
     criminal
    1.52
     adding
    1.51
     prosec
    1.46
     until
    1.40
    ouses
    1.38
     firearms
    1.37
     deport
    1.34
     parole
    1.34
    Activations Density 0.252%

    No Known Activations