© 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. 25827
    Prev
    Next
    INDEX
    Explanations

    references to telecommunications or related topics

    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
    376
    +0.15
    0.8%
    369
    +0.12
    0.7%
    175
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    175
    +0.15
    0.01
    283
    +0.12
    0.01
    275
    +0.12
    0.01
    Negative Logits
     investigators
    -1.62
     swim
    -1.60
    "?"
    -1.56
    flies
    -1.49
     defeat
    -1.38
     worms
    -1.37
     Mexican
    -1.35
     nap
    -1.35
     simulated
    -1.33
    ORM
    -1.33
    POSITIVE LOGITS
    ģ
    2.23
    ī
    2.10
    Ĩ
    2.03
    ¼
    2.02
    ultan
    2.00
    ¶
    1.96
    £
    1.94
    anguage
    1.93
    ³
    1.92
    olta
    1.91
    Activations Density 0.073%

    No Known Activations