© 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. 28708
    Prev
    Next
    INDEX
    Explanations

    occurrences 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
    10
    +0.13
    0.7%
    187
    +0.13
    0.7%
    360
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.13
    0.22
    185
    +0.13
    0.18
    165
    +0.11
    0.17
    Negative Logits
    TTP
    -1.60
     pract
    -1.50
    hops
    -1.49
     slog
    -1.48
    atra
    -1.46
    itti
    -1.45
     louder
    -1.44
    ?”
    -1.42
    elves
    -1.40
     pray
    -1.39
    POSITIVE LOGITS
    ified
    1.81
    ipolar
    1.77
    ification
    1.76
    urity
    1.67
    inal
    1.66
    ively
    1.62
     {-
    1.61
    iffe
    1.60
    culo
    1.59
    imester
    1.59
    Activations Density 0.398%

    No Known Activations