© 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. 29942
    Prev
    Next
    INDEX
    Explanations

    references to "Web"

    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
    91
    +0.14
    0.8%
    376
    +0.14
    0.8%
    369
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    91
    +0.14
    0.03
    451
    +0.14
    0.02
    341
    +0.14
    0.02
    Negative Logits
     why
    -1.53
     union
    -1.49
     same
    -1.44
     EPA
    -1.44
     tear
    -1.44
     arbitrary
    -1.42
     female
    -1.38
    arers
    -1.38
     AFL
    -1.36
     SPSS
    -1.36
    POSITIVE LOGITS
    ®
    2.38
    »¿
    2.36
    ķ
    2.35
    ª
    2.29
    ¹
    2.28
    Ī
    2.26
    ·¸
    2.23
    Ĺ
    2.16
    Ķ
    2.14
    µ
    2.13
    Activations Density 0.025%

    No Known Activations