© 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. 28757
    Prev
    Next
    INDEX
    Explanations

    returns in code segments

    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
    151
    +0.14
    0.8%
    351
    +0.13
    0.7%
    292
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    469
    +0.14
    0.06
    151
    +0.13
    0.06
    351
    +0.12
    0.06
    Negative Logits
    ¿½
    -2.52
    ²
    -2.33
    ´
    -2.31
    «
    -2.28
    »
    -2.17
    ¼
    -2.14
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -2.13
    Ģ
    -2.09
    FFIRMED
    -2.09
    §
    -2.05
    POSITIVE LOGITS
    ”,
    1.95
    eries
    1.93
    ”.
    1.75
     areas
    1.69
     scenes
    1.68
    vist
    1.64
     shots
    1.57
    uring
    1.57
     interviews
    1.55
     narratives
    1.55
    Activations Density 3.709%

    No Known Activations