© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 28030
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "search"

    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
    +0.12
    0.7%
    380
    +0.12
    0.7%
    110
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    110
    +0.12
    0.02
    349
    +0.12
    0.02
    380
    +0.12
    0.01
    Negative Logits
    ndef
    -1.67
     you
    -1.61
     knit
    -1.60
    unnumbered
    -1.60
    ustr
    -1.52
     dotted
    -1.51
    pired
    -1.50
    ynchron
    -1.49
    ux
    -1.49
     GNU
    -1.47
    POSITIVE LOGITS
    able
    1.98
    rooms
    1.97
    room
    1.95
    enger
    1.89
    force
    1.82
     engine
    1.66
     era
    1.65
    plicity
    1.64
    erville
    1.62
    fors
    1.58
    Activations Density 0.007%

    No Known Activations