© 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. 28215
    Prev
    Next
    INDEX
    Explanations

    expressions of pain or injury

    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
    +0.14
    0.8%
    148
    +0.13
    0.7%
    485
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.14
    0.02
    200
    +0.13
    0.02
    485
    +0.12
    0.02
    Negative Logits
    sel
    -1.67
    bs
    -1.56
    ASH
    -1.44
    CO
    -1.44
    ONS
    -1.40
    thood
    -1.40
     cis
    -1.40
    WA
    -1.36
    IRE
    -1.36
    QA
    -1.35
    POSITIVE LOGITS
     areas
    1.66
    ong
    1.65
    amped
    1.65
    ringes
    1.58
    imeter
    1.50
     situations
    1.49
     feelings
    1.48
     scenes
    1.47
     problem
    1.42
     (),
    1.42
    Activations Density 0.013%

    No Known Activations