© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 30922
    Prev
    Next
    INDEX
    Explanations

    references to advertisements or marketing content

    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
    111
    +0.12
    0.7%
    286
    +0.12
    0.7%
    210
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.12
    0.01
    286
    +0.12
    0.01
    210
    +0.12
    0.01
    Negative Logits
     recovering
    -1.56
     anyone
    -1.52
    upon
    -1.52
     worth
    -1.50
    urrent
    -1.47
     anybody
    -1.46
     convenient
    -1.46
     investigating
    -1.44
     Near
    -1.43
     owners
    -1.40
    POSITIVE LOGITS
    Ĵ
    3.35
    ¡
    3.25
    Ĩ
    3.15
    ¥
    3.14
    ļ
    3.14
    º
    3.04
    ĻĤ
    3.03
    £
    3.02
    Ľ
    3.00
    Ĥ¬
    2.94
    Activations Density 0.022%

    No Known Activations