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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27932
    Prev
    Next
    INDEX
    Explanations

    the article "an"

    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
    511
    +0.17
    0.9%
    223
    +0.13
    0.7%
    124
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    436
    +0.17
    0.10
    440
    +0.13
    0.10
    281
    +0.11
    0.09
    Negative Logits
     nations
    -1.65
    plates
    -1.56
     allegiance
    -1.53
    ages
    -1.53
     favor
    -1.52
     Asia
    -1.51
    hips
    -1.50
    ialize
    -1.47
     favour
    -1.45
    board
    -1.45
    POSITIVE LOGITS
    thood
    2.00
    )**
    1.70
    **\
    1.70
    ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
    1.68
    ĻĤ
    1.67
    \]\[
    1.65
     {#
    1.63
    cern
    1.58
     (\#
    1.56
    ]{.
    1.53
    Activations Density 0.211%

    No Known Activations