Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 26230
    Prev
    Next
    INDEX
    Explanations

    the pronoun "I" and variations of its usage

    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
    153
    +0.14
    0.8%
    328
    +0.13
    0.7%
    126
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.14
    0.02
    158
    +0.13
    0.04
    100
    +0.12
    0.04
    Negative Logits
     teachers
    -1.57
     exploration
    -1.51
     adults
    -1.50
     textbooks
    -1.45
     equation
    -1.45
     liquids
    -1.43
     books
    -1.41
     apples
    -1.41
    urches
    -1.38
     IDE
    -1.37
    POSITIVE LOGITS
    enza
    1.56
    ioni
    1.52
    osti
    1.51
    á̝
    1.45
    cdn
    1.45
    gress
    1.44
    à«ĩ
    1.42
    itum
    1.41
    xiv
    1.40
    ugin
    1.40
    Activations Density 0.161%

    No Known Activations