© 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. 0-MLP-SM
    11. 27162
    Prev
    Next
    INDEX
    Explanations

    instances of the word "it"

    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
    494
    +0.13
    0.7%
    41
    +0.11
    0.6%
    399
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.13
    0.22
    185
    +0.11
    0.18
    165
    +0.10
    0.17
    Negative Logits
    Ĭ
    -3.85
    IJ
    -3.75
    ī
    -3.67
    ľ
    -3.60
    ĻĤ
    -3.58
    ĩ
    -3.56
    ij
    -3.52
    į
    -3.52
    ĭ
    -3.48
    ¸
    -3.46
    POSITIVE LOGITS
     grading
    1.57
    .’”
    1.56
     multivariate
    1.53
    /@
    1.48
     families
    1.45
     ses
    1.41
    .’
    1.39
     blockade
    1.38
    :&
    1.38
    ney
    1.34
    Activations Density 0.397%

    No Known Activations