© 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. 26067
    Prev
    Next
    INDEX
    Explanations

    instances of scheduling or rescheduling events and appointments

    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
    269
    +0.15
    0.8%
    199
    +0.11
    0.6%
    218
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    218
    +0.15
    0.09
    18
    +0.11
    0.03
    475
    +0.11
    0.07
    Negative Logits
     polling
    -1.53
     keyboards
    -1.51
     murdered
    -1.49
     logger
    -1.42
     keyboard
    -1.42
     <!--
    -1.39
     share
    -1.37
     bitcoin
    -1.36
     hasht
    -1.32
    askell
    -1.31
    POSITIVE LOGITS
    Ĭ
    1.79
    ¤
    1.74
    ĩ
    1.63
    Ĺ
    1.62
    ¡
    1.59
    Ģ
    1.56
    ľ
    1.54
    «
    1.54
    ª
    1.53
    ¬
    1.53
    Activations Density 1.953%

    No Known Activations