© 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. 27212
    Prev
    Next
    INDEX
    Explanations

    repetitive references to promotional content or promotional phrases

    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%
    58
    +0.12
    0.7%
    139
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    58
    +0.14
    0.01
    16
    +0.12
    0.01
    508
    +0.11
    0.01
    Negative Logits
    OVA
    -1.58
    Ļª
    -1.55
    MSO
    -1.54
     mean
    -1.51
    ickness
    -1.48
    ingle
    -1.48
     horizon
    -1.47
    ĨĴ
    -1.46
    rific
    -1.45
    GREEK
    -1.43
    POSITIVE LOGITS
    etheus
    1.90
    hole
    1.75
    stown
    1.72
    inent
    1.62
    holes
    1.49
    ega
    1.44
    inence
    1.43
    elyn
    1.42
    eted
    1.40
    ats
    1.38
    Activations Density 0.152%

    No Known Activations