© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29330
    Prev
    Next
    INDEX
    Explanations

    the pronoun "it" in various contexts

    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
    123
    +0.14
    0.8%
    67
    +0.13
    0.7%
    406
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.14
    0.22
    185
    +0.13
    0.18
    165
    +0.13
    0.17
    Negative Logits
    ±
    -3.70
    °
    -3.53
    £
    -3.51
    Ŀ
    -3.49
    ¯
    -3.43
    µ
    -3.42
    ¨
    -3.28
    Ī
    -3.25
    ķ
    -3.25
    ¥
    -3.23
    POSITIVE LOGITS
     Elementary
    1.52
     pace
    1.44
     Bluetooth
    1.44
    itation
    1.43
     proposition
    1.42
    eness
    1.41
     beg
    1.41
     Hilbert
    1.41
     experience
    1.40
     Banach
    1.38
    Activations Density 0.421%

    No Known Activations