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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27725
    Prev
    Next
    INDEX
    Explanations

    instances of the word "connecting"

    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
    376
    +0.20
    1.1%
    457
    +0.16
    0.9%
    256
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    256
    +0.20
    0.01
    457
    +0.16
    0.01
    329
    +0.16
    0.01
    Negative Logits
    onse
    -1.53
    ausing
    -1.39
     recent
    -1.36
    ying
    -1.35
     committed
    -1.34
    iding
    -1.34
    cele
    -1.33
    ellow
    -1.32
     famous
    -1.32
    ooting
    -1.31
    POSITIVE LOGITS
     thereto
    2.03
     them
    1.95
    feit
    1.87
    thon
    1.80
     dots
    1.71
     gaps
    1.66
     parts
    1.52
     him
    1.51
     equations
    1.47
     obstacles
    1.45
    Activations Density 0.005%

    No Known Activations