© 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 EvalsExportsinterp-engineNEWAPI 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. 29504
    Prev
    Next
    INDEX
    Explanations

    sections of text that reference links or URLs

    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
    321
    +0.14
    0.9%
    435
    +0.12
    0.7%
    26
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    321
    +0.14
    0.01
    435
    +0.12
    0.01
    26
    +0.11
    0.01
    Negative Logits
    teral
    -1.46
    NEY
    -1.46
     closed
    -1.45
     transmitted
    -1.41
     opened
    -1.38
    aning
    -1.38
     ORDERED
    -1.37
    ANT
    -1.35
    oxacin
    -1.35
     detected
    -1.35
    POSITIVE LOGITS
    !/
    2.07
    ,...
    1.79
    .
    1.75
    º
    1.69
    ļ
    1.68
    subsec
    1.66
    ¼
    1.62
     bras
    1.60
     [âĢ¦]
    1.59
    cule
    1.59
    Activations Density 0.008%

    No Known Activations