© 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. 30539
    Prev
    Next
    INDEX
    Explanations

    questions or inquiries within the text

    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
    356
    +0.13
    0.7%
    457
    +0.12
    0.7%
    85
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    356
    +0.13
    0.05
    85
    +0.12
    0.05
    197
    +0.11
    0.04
    Negative Logits
    OPE
    -1.52
     </
    -1.48
     SUMMARY
    -1.47
    ¬
    -1.47
    HTML
    -1.43
    ATIONAL
    -1.43
     www
    -1.41
    antly
    -1.41
    agle
    -1.40
    ...](
    -1.39
    POSITIVE LOGITS
    osi
    1.59
    mand
    1.49
    vu
    1.48
     conditions
    1.45
    soever
    1.43
    ilda
    1.42
    abad
    1.42
    ário
    1.40
    ovic
    1.39
    ard
    1.37
    Activations Density 0.026%

    No Known Activations