Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27351
    Prev
    Next
    INDEX
    Explanations

    instances of the word "hypothermia."

    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
    156
    +0.17
    0.9%
    376
    +0.14
    0.8%
    364
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    317
    +0.17
    0.01
    453
    +0.14
    0.01
    450
    +0.13
    0.01
    Negative Logits
    »¿
    -3.12
    ĥ½
    -3.10
    ĵ
    -2.71
    ¿½
    -2.55
    ¿
    -2.35
    ĸ´
    -2.33
    ĭ
    -2.30
    Ĥ¬
    -2.27
    ĥ
    -2.27
    ¼
    -2.27
    POSITIVE LOGITS
     prem
    1.68
     offence
    1.67
     pains
    1.60
     session
    1.53
     regime
    1.53
     workload
    1.52
     offender
    1.51
     scheme
    1.47
    asio
    1.41
     DV
    1.41
    Activations Density 0.018%

    No Known Activations