© 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. 2-MLP-SM
    11. 26468
    Prev
    Next
    INDEX
    Explanations

    mentions of websites and related terms

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    417
    +0.14
    0.8%
    110
    +0.13
    0.7%
    86
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    417
    +0.14
    0.04
    120
    +0.13
    0.04
    311
    +0.12
    0.03
    Negative Logits
     websites
    -1.55
    www
    -1.52
     Sunday
    -1.50
    apers
    -1.50
    aturday
    -1.49
    č↵
    -1.44
     anyone
    -1.44
    acts
    -1.36
    rones
    -1.34
     Saturday
    -1.32
    POSITIVE LOGITS
    "}](#
    1.79
    ishly
    1.61
     dich
    1.57
     differently
    1.56
    sense
    1.49
    ableness
    1.42
    lee
    1.40
    lane
    1.34
    zzi
    1.31
     reck
    1.30
    Activations Density 0.186%

    No Known Activations