© 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. 25960
    Prev
    Next
    INDEX
    Explanations

    instances of writing 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
    420
    +0.11
    0.6%
    370
    +0.10
    0.6%
    262
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.11
    0.04
    311
    +0.10
    0.03
    2
    +0.10
    0.02
    Negative Logits
    bos
    -1.60
     ourselves
    -1.60
    walks
    -1.57
    arians
    -1.56
    ingo
    -1.54
    ARY
    -1.53
    ATED
    -1.53
    ABLE
    -1.52
    prehens
    -1.52
     alike
    -1.48
    POSITIVE LOGITS
    ²
    2.16
    ¶
    2.11
    ł
    2.10
    ³
    2.06
    ļ
    2.06
    ®
    1.97
    µ
    1.86
    ¥
    1.79
    ¾
    1.77
    ¤
    1.73
    Activations Density 0.289%

    No Known Activations