© 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. 26102
    Prev
    Next
    INDEX
    Explanations

    the word "You" and its variations, indicating an emphasis on direct address to the reader or audience

    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
    134
    +0.13
    0.8%
    181
    +0.13
    0.7%
    98
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    134
    +0.13
    0.06
    470
    +0.13
    0.06
    181
    +0.11
    0.05
    Negative Logits
     okay
    -1.45
     whole
    -1.44
     ugly
    -1.44
    eu
    -1.43
     prudent
    -1.41
     goodbye
    -1.41
    ++){
    -1.39
     white
    -1.38
     done
    -1.37
    done
    -1.33
    POSITIVE LOGITS
    ument
    1.62
    eries
    1.59
    ption
    1.57
    ulations
    1.54
    ţ
    1.54
    ality
    1.53
    compat
    1.50
    ician
    1.45
    Pub
    1.44
    ytics
    1.43
    Activations Density 0.248%

    No Known Activations