© 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. 28028
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "tens"

    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
    477
    +0.15
    0.8%
    315
    +0.15
    0.8%
    144
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    315
    +0.15
    0.02
    19
    +0.15
    0.01
    144
    +0.14
    0.01
    Negative Logits
     biomarkers
    -1.56
     candidates
    -1.44
     Asst
    -1.42
     vulnerable
    -1.38
     neither
    -1.34
    scar
    -1.33
     candidate
    -1.32
     mean
    -1.32
     markers
    -1.31
     integrity
    -1.30
    POSITIVE LOGITS
    »¿
    3.32
    »
    3.31
    µ
    3.31
    º
    3.19
    ĥ½
    3.15
    ↵
    3.11
    ↵
    3.11
    ↵
    3.11
                  ↵
    3.11
    ↵
    3.11
    Activations Density 0.101%

    No Known Activations